Importing Dataset

# Importing required libraries
import pandas as pd
import numpy as np
import plotly.express as plx
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import sklearn
from sklearn.metrics import r2_score, mean_absolute_error, mean_squared_error
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
import time
from tqdm import tqdm

# Column names writtened in a list to apply while importing csv file from the dataset location
column_names = ['CIC0','SM1_Dz(Z)','GATS1i','NdsCH','NdssC','MLOGP', 'LC50']

# The data in the csv file is separated with colon(;), so we set the delimiter as ';'
data = pd.read_csv('C:\\Users\\harip\\INEURON_PROJECTS\\Prediction of LC50\\LC50_Project\\data\\dataset(csv)\\qsar_fish_toxicity.csv', header = None, delimiter = ';', names = column_names)

# Looking at the data
data

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50
0	3.260	0.829	1.676	0	1	1.453	3.770
1	2.189	0.580	0.863	0	0	1.348	3.115
2	2.125	0.638	0.831	0	0	1.348	3.531
3	3.027	0.331	1.472	1	0	1.807	3.510
4	2.094	0.827	0.860	0	0	1.886	5.390
...	...	...	...	...	...	...	...
903	2.801	0.728	2.226	0	2	0.736	3.109
904	3.652	0.872	0.867	2	3	3.983	4.040
905	3.763	0.916	0.878	0	6	2.918	4.818
906	2.831	1.393	1.077	0	1	0.906	5.317
907	4.057	1.032	1.183	1	3	4.754	8.201

908 rows × 7 columns

Dataset Information

data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 908 entries, 0 to 907
Data columns (total 7 columns):
 #   Column     Non-Null Count  Dtype  
---  ------     --------------  -----  
 0   CIC0       908 non-null    float64
 1   SM1_Dz(Z)  908 non-null    float64
 2   GATS1i     908 non-null    float64
 3   NdsCH      908 non-null    int64  
 4   NdssC      908 non-null    int64  
 5   MLOGP      908 non-null    float64
 6   LC50       908 non-null    float64
dtypes: float64(5), int64(2)
memory usage: 49.8 KB

There's no null values in the dataset.

Handling Duplicates

Here, we're removing duplicates in the Dataset

def handling_duplicates(data):
    if data.duplicated().sum() > 0:
        print(f"There's a {data.duplicated().sum()} duplicated record in the dataset and removed successfully.")
        print("The Data passed the 'duplicates_handling()' and moved to check datatypes of the features")
        data.drop_duplicates(inplace=True)
    else:
        print("[data_transformation.py] While Handling the data, there's no duplicates.") 
    return data

handling_duplicates(data)

There's a 1 duplicated record in the dataset and removed successfully.
The Data passed the 'duplicates_handling()' and moved to check datatypes of the features

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50
0	3.260	0.829	1.676	0	1	1.453	3.770
1	2.189	0.580	0.863	0	0	1.348	3.115
2	2.125	0.638	0.831	0	0	1.348	3.531
3	3.027	0.331	1.472	1	0	1.807	3.510
4	2.094	0.827	0.860	0	0	1.886	5.390
...	...	...	...	...	...	...	...
903	2.801	0.728	2.226	0	2	0.736	3.109
904	3.652	0.872	0.867	2	3	3.983	4.040
905	3.763	0.916	0.878	0	6	2.918	4.818
906	2.831	1.393	1.077	0	1	0.906	5.317
907	4.057	1.032	1.183	1	3	4.754	8.201

907 rows × 7 columns

Checking Datatypes of Features in the Dataset

Here, we're checking the data type of each feature. So, the conflicts in future on features of Dataset will be avoided earlier.

def get_check_dtypes(data):
    df_types = pd.DataFrame(data.dtypes)
    df_types.reset_index(inplace=True)
    df_types.rename(columns={'index': 'col_name', 0: 'data_type'}, inplace=True)
    print("Got Datatypes of each column successfully")

    problamatic_column = []
    for i in range(len(df_types)):
        if str(df_types['data_type'][i]).__contains__('int') or str(df_types['data_type'][i]).__contains__('float'):
            pass 
        else:
            problamatic_column.append(df_types['col_name'][i])

    if len(problamatic_column) == 0:
        print("There is no problem with the datatype of each column. The data passed 'get_check_dtypes()' successfully.")
        return data
    else:
        print(f"There is a problem with the datatype of column -> {problamatic_column}")
        print("The data holds non-numeric feature, then the data is not moved further in this project. Please resolve this!!")

get_check_dtypes(data)

Got Datatypes of each column successfully
There is no problem with the datatype of each column. The data passed 'get_check_dtypes()' successfully.

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50
0	3.260	0.829	1.676	0	1	1.453	3.770
1	2.189	0.580	0.863	0	0	1.348	3.115
2	2.125	0.638	0.831	0	0	1.348	3.531
3	3.027	0.331	1.472	1	0	1.807	3.510
4	2.094	0.827	0.860	0	0	1.886	5.390
...	...	...	...	...	...	...	...
903	2.801	0.728	2.226	0	2	0.736	3.109
904	3.652	0.872	0.867	2	3	3.983	4.040
905	3.763	0.916	0.878	0	6	2.918	4.818
906	2.831	1.393	1.077	0	1	0.906	5.317
907	4.057	1.032	1.183	1	3	4.754	8.201

907 rows × 7 columns

Handling Missing Data

Here, we're just trying to handle the missing value. If there's no missing values, no issues the data is revert back in original form

# Here, we're just trying to handle the missing value. If there's no missing values, no issues the data is revert back in original form
def handling_missing_values(data):
    try:
        data_dep = data['LC50']
        data_indp = data.drop(['LC50'], axis=1)
        mean_impute_cols = ['CIC0', 'SM1_Dz(Z)', 'GATS1i', 'MLOGP']
        mode_impute_cols = ['NdsCH', 'NdssC']
        transformer = ColumnTransformer(transformers=[
            ("tf1", SimpleImputer(strategy='mean'), mean_impute_cols),
            ("tf2", SimpleImputer(strategy='most_frequent'), mode_impute_cols)
        ])
        trans_data = transformer.fit_transform(data_indp)
        column_names = ['CIC0','SM1_Dz(Z)','GATS1i','MLOGP','NdsCH','NdssC']
        new_data = pd.DataFrame(trans_data, columns=column_names)
        new_data['LC50'] = list(data_dep)
        # Sometimes, there's a chance of duplicates in target variable. So, we've to remove that too
        new_data = new_data.dropna()
        data = pd.DataFrame()
        # Column order is changed due to ColumnTransformer. So, we're reverting back to original form
        for x in column_names:
            data[x] = new_data[x]
        data['LC50'] = list(data_dep)
        print("The data has passed 'handling_missing_values()' successfully.")
        return data
    except:
        print("The data won't received 'handling_missing_values()'. So, please resolve this problem.")

handling_missing_values(data)

The data has passed 'handling_missing_values()' successfully.

C:\Users\harip\anaconda3\lib\site-packages\sklearn\impute\_base.py:49: FutureWarning: Unlike other reduction functions (e.g. `skew`, `kurtosis`), the default behavior of `mode` typically preserves the axis it acts along. In SciPy 1.11.0, this behavior will change: the default value of `keepdims` will become False, the `axis` over which the statistic is taken will be eliminated, and the value None will no longer be accepted. Set `keepdims` to True or False to avoid this warning.
  mode = stats.mode(array)

	CIC0	SM1_Dz(Z)	GATS1i	MLOGP	NdsCH	NdssC	LC50
0	3.260	0.829	1.676	1.453	0.0	1.0	3.770
1	2.189	0.580	0.863	1.348	0.0	0.0	3.115
2	2.125	0.638	0.831	1.348	0.0	0.0	3.531
3	3.027	0.331	1.472	1.807	1.0	0.0	3.510
4	2.094	0.827	0.860	1.886	0.0	0.0	5.390
...	...	...	...	...	...	...	...
902	2.801	0.728	2.226	0.736	0.0	2.0	3.109
903	3.652	0.872	0.867	3.983	2.0	3.0	4.040
904	3.763	0.916	0.878	2.918	0.0	6.0	4.818
905	2.831	1.393	1.077	0.906	0.0	1.0	5.317
906	4.057	1.032	1.183	4.754	1.0	3.0	8.201

907 rows × 7 columns

From the above heatmap, we know that 'MLOGP' is the most important independent variable(having high postive correlation = 0.65), then 'SM1_Dz(Z)' having postive correlation of 0.41, then 'GATS1i' having negative correlation of -3.9. Rest of the features having less correlation with repect to the target variable (LC50).

Explorartory Data Analysis

# Scatter plot of feature 'CIC0'
plx.scatter(x = data['CIC0'])

# Scatter plot of feature 'SM1_Dz(Z)'
plx.scatter(x = data['SM1_Dz(Z)'] )

# Scatter plot of feature 'GATS1i'
plx.scatter(x = data['GATS1i'])

NdsCH & NdsCH is a categorical feature, we can check how many of records belongs to each category

data['NdsCH'].unique()

array([0, 1, 3, 2, 4], dtype=int64)

data['NdsCH'].value_counts()

0    759
1    107
2     29
4      7
3      5
Name: NdsCH, dtype: int64

ndsch_df = pd.DataFrame(data['NdsCH'].value_counts())

ndsch_df

	NdsCH
0	759
1	107
2	29
4	7
3	5

ndsch_df = ndsch_df.rename_axis('category').reset_index()

ndsch_df

	category	NdsCH
0	0	759
1	1	107
2	2	29
3	4	7
4	3	5

fig = plx.bar(x = ndsch_df['category'], y = ndsch_df['NdsCH'])
fig.update_traces(dict(marker_line_width=0))
fig.show()

Out of 908 record, 760 record belongs to the category 0 of 'NdsCH'

data['NdssC'].unique()

array([1, 0, 3, 2, 4, 5, 6], dtype=int64)

data['NdssC'].value_counts()

0    621
1    176
2     81
3     18
4      8
6      2
5      1
Name: NdssC, dtype: int64

ndssc_df = pd.DataFrame(data['NdssC'].value_counts())

ndssc_df

	NdssC
0	621
1	176
2	81
3	18
4	8
6	2
5	1

ndssc_df = ndssc_df.rename_axis('category').reset_index()

ndssc_df

	category	NdssC
0	0	621
1	1	176
2	2	81
3	3	18
4	4	8
5	6	2
6	5	1

fig = plx.bar(x = ndssc_df['category'], y = ndssc_df['NdssC'])
fig.update_traces(dict(marker_line_width=0))
fig.show()

Here, 'NdssC' feature has a '0' category as most, then '1' '2' and so on...

# Scatter plot on 'MLOGP' feature
plx.scatter(x = data['MLOGP'])

# Scatter plot on 'LC50' feature
plx.scatter(x = data['LC50'])

Outlier Detection

Have to detect outliers before developinga model. Here, there are 6 independent features. Out of 6, 4 are Continuous data. By using box plot, we're checking the presence of outliers

plx.box(data, x = data['CIC0'])

plx.box(data, x = data['SM1_Dz(Z)'])

plx.box(data, x = data['GATS1i'])

plx.box(data, x = data['MLOGP'])

All 4 independent features of continuous data having outliers.

Here, we're not going to remove any outlier because the dataset is small containing only 908 records..

Handling Outliers(Technique used : Quantile based flooring and capping)

We can remove outliers when the dataset is large. But, here the dataset having 908 records only. There are soo many options to replace the outlier value. For example we can replace it with mean or median. Here, we used the technique called "Quantile based flooring and Capping". So, the outliers which is less than the lower bound is replace by 10th percentile of the data and the outliers which is greater than upper bound is replaced by 90th percentile of the data.

def compute_outlier(data, col):
    values=data[col]
    q1=np.percentile(values,25)
    q3=np.percentile(values,75)
    iqr=q3-q1
    lower_bound=q1-(1.5*iqr)
    upper_bound=q3+(1.5*iqr)
    tenth_percentile=np.percentile(values,10)
    ninetieth_percentile=np.percentile(values,90)
    return tenth_percentile, ninetieth_percentile, lower_bound, upper_bound

def handling_outlier(data):
    to_handle_cols=['CIC0', 'SM1_Dz(Z)', 'GATS1i', 'MLOGP']
    for col in to_handle_cols:
        tenth_percentile, ninetieth_percentile, lower_bound, upper_bound=compute_outlier(data, col)
        data.loc[data[col]<lower_bound, col]=tenth_percentile
        data.loc[data[col]>upper_bound, col]=ninetieth_percentile
    print("Outliers handled successfully in 'handling_outlier()'.")
    return data

handling_outlier(data)

Outliers handled successfully in 'handling_outlier()'.

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50
0	3.260	0.829	1.676	0	1	1.453	3.770
1	2.189	0.580	0.863	0	0	1.348	3.115
2	2.125	0.638	0.831	0	0	1.348	3.531
3	3.027	0.331	1.472	1	0	1.807	3.510
4	2.094	0.827	0.860	0	0	1.886	5.390
...	...	...	...	...	...	...	...
903	2.801	0.728	2.226	0	2	0.736	3.109
904	3.652	0.872	0.867	2	3	3.983	4.040
905	3.763	0.916	0.878	0	6	2.918	4.818
906	2.831	1.393	1.077	0	1	0.906	5.317
907	4.057	1.032	1.183	1	3	4.754	8.201

907 rows × 7 columns

We can cross check whether the outliers were handled or not!!!

1) CIC0

plx.box(data['CIC0'])

2) SM1_Dz(Z)

plx.box(data['SM1_Dz(Z)'])

3) GATS1i

plx.box(data['GATS1i'])

4) MLOGP

plx.box(data['MLOGP'])

Short Statistical info

describe() method gives us some statistical information of the data like., data count, mean, standard deviation, 25th percentile, 50th percentile, etc....

# describe() gives some statistical information of the dataset.
data.describe()

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50
count	907.000000	907.000000	907.000000	907.000000	907.000000	907.000000	907.000000
mean	2.897714	0.625782	1.287370	0.229327	0.486218	2.112877	4.064723
std	0.741028	0.421883	0.378049	0.605621	0.861603	1.393402	1.456475
min	0.965000	0.000000	0.396000	0.000000	0.000000	-1.358000	0.053000
25%	2.346000	0.223000	0.951000	0.000000	0.000000	1.209000	3.151500
50%	2.937000	0.570000	1.244000	0.000000	0.000000	2.127000	3.991000
75%	3.407000	0.894500	1.562500	0.000000	1.000000	3.105000	4.909000
max	4.880000	1.860000	2.456000	4.000000	6.000000	5.934000	9.612000

Correlation

# Correlation gives how every attribute is important with each other
plx.imshow(data.corr(), text_auto = True, height = 700, width = 700)

From the above correlation graph we got some useful insights. They are,

1) The feature 'MLOGP' is the most important feature for the target variable 'LC50' with correlation of 0.6580

2) Next to 'MLOGP', 'SM1_Dz(Z)' is the important feature for target variable 'LC50' with correlation of 0.4119

3) The feature 'GATS1i' is negatively correlated, not that much high. The correlation value is -0.3878

4) 'NdsCH' and 'NdssC' are the most least important feature with respect to target 'LC50'

Dimensionality Reduction

We can remove any one the independent features which is highly correlated with other independent feature.

def dimensionality_reduction(data, threshold):
    # We, get threshold from user. So, that the feature is removed above the threshold.
    temp_data = data.drop(['LC50'], axis=1)
    corr_columns = set() # Here, the data structure 'set()' is used avoid the duplicate column names.
    corr_matrix = temp_data.corr() # object.corr() returns the correlation matrix of the dataset.
    # This for loop coves only the left bottom of correlation table. So, 
    for i in range(len(corr_matrix.columns)):
        for j in range(i):
            # If the correlation is greater than threshold, the column name is added to the set 'corr_columns'.
            if corr_matrix.iloc[i,j] > threshold:  
                column_name = corr_matrix.columns[i]
                corr_columns.add(column_name)
    data.drop(list(corr_columns), axis=1, inplace=True)
    if len(list(corr_columns)) == 0:
        print("Dimensionality Reduction not happened because of low correlation between independent features.")
    else:
        print("Dimensionality reduction successfully completed.")
    return data

dimensionality_reduction(data, 0.85)

Dimensionality Reduction not happened because of low correlation between independent features.

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50
0	3.260	0.829	1.676	0	1	1.453	3.770
1	2.189	0.580	0.863	0	0	1.348	3.115
2	2.125	0.638	0.831	0	0	1.348	3.531
3	3.027	0.331	1.472	1	0	1.807	3.510
4	2.094	0.827	0.860	0	0	1.886	5.390
...	...	...	...	...	...	...	...
903	2.801	0.728	2.226	0	2	0.736	3.109
904	3.652	0.872	0.867	2	3	3.983	4.040
905	3.763	0.916	0.878	0	6	2.918	4.818
906	2.831	1.393	1.077	0	1	0.906	5.317
907	4.057	1.032	1.183	1	3	4.754	8.201

907 rows × 7 columns

Splitting Data into Train and Test set

from sklearn.model_selection import train_test_split
x_train, x_test,y_train, y_test = train_test_split(data.drop(['LC50'], axis=1), data['LC50'], test_size=0.2)

Functions

model_name, r2_score_, mae,rmse,mse,error_0_to_1, error_1_to_2, error_2_to_3, error_greater_than_3, training_time, prediction_time = [],[],[],[],[],[],[],[],[],[],[]

# Using 'time' package, we're capturing the training and prediction time of the model
def model_trainer(model, x_train, y_train, x_test):
    start_time = time.time()
    model = model.fit(x_train, y_train)
    training_time = time.time()-start_time
    start_time = time.time()
    pred_y_test = model.predict(x_test)
    prediction_time = time.time()-start_time
    pred_y_train = model.predict(x_train)
    return pred_y_test, pred_y_train, training_time, prediction_time

def calculate_error_range(pred, y_test):
        error=[]
        zero_to_one,one_to_two,two_to_three,greater_than_three=0,0,0,0
        for i in range(len(y_test)):
            error.append(abs(pred[i]-list(y_test)[i]))
        for x in error:
            if (x>=0) & (x<=1):
                zero_to_one+=1
            elif (x>1) & (x<=2):
                one_to_two+=1
            elif (x>2) & (x<=3):
                two_to_three+=1
            elif (x>3):
                greater_than_three+=1
        return error, zero_to_one, one_to_two, two_to_three, greater_than_three

def visualize_error(error, modelname):
    # Plotting those absolute error values in scatter plot gives us an idea that how modelis performing in the test data.
    # Code to check in which error range the predicted values lies. The ranges are 0-1, 1-2, 2-3 and >3.
    zero_to_one,zero_to_one_idx, one_to_two,one_to_two_idx, two_to_three,two_to_three_idx, grt_than_three,grt_than_three_idx = [],[],[],[],[],[],[],[]
    for i in range(len(error)):
        if (error[i]>=0) & (error[i]<=1):
            zero_to_one.append(error[i])
            zero_to_one_idx.append(i)
        elif (error[i]>1) & (error[i]<=2):
            one_to_two.append(error[i])
            one_to_two_idx.append(i)
        elif (error[i]>2) & (error[i]<=3):
            two_to_three.append(error[i])
            two_to_three_idx.append(i)
        elif error[i]>3:
            grt_than_three.append(error[i])
            grt_than_three_idx.append(i)

    fig = go.Figure()
    fig.add_trace(go.Scatter(y=zero_to_one,x=zero_to_one_idx,
                        mode='markers',
                        name='0 to 1'))
    fig.add_trace(go.Scatter(y=one_to_two,x=one_to_two_idx,
                        mode='markers',
                        name='1 to 2'))
    fig.add_trace(go.Scatter(y=two_to_three,x=two_to_three_idx,
                        mode='markers',
                        name='2 to 3'))
    fig.add_trace(go.Scatter(y=grt_than_three,x=grt_than_three_idx,
                        mode='markers',
                        name='>3'))
    fig.update_layout(
        title=f"Absolute Difference b/w Predicted and Actual value of {modelname}",
        xaxis_title="Index",
        yaxis_title="Error",
        legend_title_text="Error Range",
        font=dict(
            family="Courier New, monospace",
            size=13,
            color="RebeccaPurple"
        )
    )
    fig.show()

def visulaize_performance_of_the_model(pred, y_test, modelname):
    # Plotting both line & scatter plot in same graph of predicted values to check the performance of the model in visualization.
    fig = go.Figure()
    fig.add_trace(go.Scatter(x=np.arange(0,11), y=np.arange(0,11),
                             mode='lines',
                             name='perfectline'))
    fig.add_trace(go.Scatter(x=pred, y=y_test,
                             mode='markers',
                             name='predictions'))
    fig.update_layout(
        title=f"Performance of {modelname} on Test data",
        xaxis_title="Predicted",
        yaxis_title="Actual",
        font=dict(
            family="Courier New, monospace",
            size=13,
            color="RebeccaPurple"
        )
    )
    fig.show()

def visualize_prediction_on_traindata(pred_y_train, y_train ,modelname):
    # To check whether the model is overfitted or not, we're predicting the target value for train set and visualized like above plot.
    fig = go.Figure()
    fig.add_trace(go.Scatter(x=np.arange(0,11), y=np.arange(0,11),
                             mode='lines',
                             name='perfectline'))
    fig.add_trace(go.Scatter(x=pred_y_train, y=y_train,
                             mode='markers',
                             name='predictions'))
    fig.update_layout(
        title=f"{modelname} model on Training data to check Overfitting",
        xaxis_title="Predicted",
        yaxis_title="Actual",
        font=dict(
            family="Courier New, monospace",
            size=13,
            color="RebeccaPurple"
        )
    )
    fig.show()

def recorddata(modelname, pred_y_test, y_test, zero_to_one, one_to_two, two_to_three, greater_than_three, trn_time, pred_time):
    # details like modelname, error range, scores of the model(r2, rmse, mse, mae),prediction time, training time were recorded.
    model_name.append(modelname)
    r2_score_.append(r2_score(y_test, pred_y_test))
    mae.append(mean_absolute_error(y_test, pred_y_test))
    mse.append(mean_squared_error(y_test, pred_y_test))
    rmse.append(np.sqrt(mean_squared_error(y_test, pred_y_test)))
    error_0_to_1.append(zero_to_one)
    error_1_to_2.append(one_to_two)
    error_2_to_3.append(two_to_three)
    error_greater_than_3.append(greater_than_three)
    training_time.append(trn_time)
    prediction_time.append(pred_time)

Multiple Linear Regression

# Importing LinearRegression from sklearn.linear_model
from sklearn.linear_model import LinearRegression 

modelname = 'MultipleLinearRegression'

pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(LinearRegression(), x_train, y_train, x_test)

trn_time

0.10857486724853516

pred_time

0.002001047134399414

error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)

zero_to_one, one_to_two, two_to_three, greater_than_three

(133, 38, 8, 3)

visualize_error(error, modelname)

The above scatter plots shows that most of the predicted values having error from 0 to 1(blue plots). Some of Error lies between 1 and 2(red plots), few of the between 2 and 3(green plots). Only few at the top having error more than 3.0

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

This model is a good prediction, the predictions(red markers) are pointed closer to the blue line(perfect line). At the same time, we have to check whether the model is overfitted with training set or not...

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

From the graph itself we can say that, this model is not overfitted and this is a generalised model. So, we can consider this model for final evaluation.

recorddata(modelname, pred_y_test, y_test, zero_to_one, one_to_two, two_to_three, greater_than_three, trn_time, pred_time)

model_name, r2_score_, mae,rmse,mse,error_0_to_1, error_1_to_2, error_2_to_3, error_greater_than_3, trn_time, pred_time

(['MultipleLinearRegression'],
 [0.5881944916179406],
 [0.7570821537162007],
 [1.022582311321646],
 [1.0456745834279195],
 [133],
 [38],
 [8],
 [3],
 0.10857486724853516,
 0.002001047134399414)

Ridge Regressor

# Importing Ridge package from sklearn.linear_model
from sklearn.linear_model import Ridge

modelname = 'RidgeRegression'
pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(Ridge(), x_train, y_train, x_test)
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

The above scatter plots shows that most of the predicted values having error from 0 to 1(blue plots). Some of Error lies between 1 and 2(red plots), few of the between 2 and 3(green plots). Some of points at the top having error more than 3.0

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

This model is quite good in prediction, only one point having a big error. It looks same as the graph from Linear Regression. At the same time, we have to check whether the model is overfitted with training set or not...

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

From the graph itself we can say that, this model is not overfitted and this is a generalised model. So, we can consider this model for final evaluation.

recorddata(modelname, pred_y_test, y_test, zero_to_one, one_to_two, two_to_three, greater_than_three, trn_time, pred_time)
model_name, r2_score_, mae,rmse,mse,error_0_to_1, error_1_to_2, error_2_to_3, error_greater_than_3, trn_time, pred_time

(['MultipleLinearRegression', 'RidgeRegression'],
 [0.5881944916179406, 0.5882574872756139],
 [0.7570821537162007, 0.7576445993512019],
 [1.022582311321646, 1.0225040939257053],
 [1.0456745834279195, 1.0455146220948277],
 [133, 133],
 [38, 38],
 [8, 8],
 [3, 3],
 0.006402492523193359,
 0.0024585723876953125)

Hyper-parameter Tuning on Ridge Regressor

"""
RandomizedSearchCV is used for hyper-parameter tuning. This 'RandomizedSearchCV' picks appropriate parameter and 
gives us best out of it.
"""
from sklearn.model_selection import RandomizedSearchCV

# A dictionary 'params' having some important parameter as keys which holds list of different values
params = {
    'alpha' : [0, 1e-10,1e-9,1e-8,1e-7,1e-6,1e-5,1e-4,1e-3,1e-2,1e-1,1,5,10,15,20,25,30,35,40,50,60,70,80,90,100,150,200],
    'max_iter' : [100, 200,300,400, 500,600,700,800,900, 1000, 1500, 2000],
    'solver' : ['auto', 'svd', 'cholesky', 'lsqr', 'sparse_cg', 'sag', 'saga', 'lbfgs']
         }

"""
The Ridge() is assigned as an estimator, 'params' dictionary is assigned as an param_distributions and 
RandomizedSearchCV and 'r2' metric is assigned as a scoring metric of 'RandomizedSearchCV()' and stored in a variable
'ridge_tuned'
"""
ridge_tuned = RandomizedSearchCV(Ridge(), param_distributions=params, scoring = 'r2')

# Have to fit x_train and y_train for the variable 'ridge_tuned'
ridge_tuned.fit(x_train, y_train)

C:\Users\harip\anaconda3\lib\site-packages\sklearn\model_selection\_validation.py:372: FitFailedWarning:


20 fits failed out of a total of 50.
The score on these train-test partitions for these parameters will be set to nan.
If these failures are not expected, you can try to debug them by setting error_score='raise'.

Below are more details about the failures:
--------------------------------------------------------------------------------
20 fits failed with the following error:
Traceback (most recent call last):
  File "C:\Users\harip\anaconda3\lib\site-packages\sklearn\model_selection\_validation.py", line 680, in _fit_and_score
    estimator.fit(X_train, y_train, **fit_params)
  File "C:\Users\harip\anaconda3\lib\site-packages\sklearn\linear_model\_ridge.py", line 1011, in fit
    return super().fit(X, y, sample_weight=sample_weight)
  File "C:\Users\harip\anaconda3\lib\site-packages\sklearn\linear_model\_ridge.py", line 705, in fit
    raise ValueError(
ValueError: 'lbfgs' solver can be used only when positive=True. Please use another solver.


C:\Users\harip\anaconda3\lib\site-packages\sklearn\model_selection\_search.py:969: UserWarning:

One or more of the test scores are non-finite: [0.55508382        nan        nan 0.56751987 0.56305301        nan
 0.56752329        nan 0.56750961 0.50586877]

RandomizedSearchCV(estimator=Ridge(),
                   param_distributions={'alpha': [0, 1e-10, 1e-09, 1e-08, 1e-07,
                                                  1e-06, 1e-05, 0.0001, 0.001,
                                                  0.01, 0.1, 1, 5, 10, 15, 20,
                                                  25, 30, 35, 40, 50, 60, 70,
                                                  80, 90, 100, 150, 200],
                                        'max_iter': [100, 200, 300, 400, 500,
                                                     600, 700, 800, 900, 1000,
                                                     1500, 2000],
                                        'solver': ['auto', 'svd', 'cholesky',
                                                   'lsqr', 'sparse_cg', 'sag',
                                                   'saga', 'lbfgs']},
                   scoring='r2')

# To get best parameter of tuned Ridge Regressor
ridge_tuned.best_params_

{'solver': 'saga', 'max_iter': 1000, 'alpha': 1e-10}

modelname = 'RidgeRegression Tuned'
pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(Ridge().set_params(**ridge_tuned.best_params_), x_train, y_train, x_test)
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

The plot looks same as the un-tuned Ridge Regression.

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

This model is quite good in prediction, only one point having a big error. At the same time, we have to check whether the model is overfitted with training set or not...

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

From the graph itself we can say that, this model is not overfitted and this is a generalised model. So, we can consider this model for final evaluation. Not that much difference after tuning.

recorddata(modelname, pred_y_test, y_test, zero_to_one, one_to_two, two_to_three, greater_than_three, trn_time, pred_time)
model_name, r2_score_, mae,rmse,mse,error_0_to_1, error_1_to_2, error_2_to_3, error_greater_than_3, trn_time, pred_time

(['MultipleLinearRegression', 'RidgeRegression', 'RidgeRegression Tuned'],
 [0.5881944916179406, 0.5882574872756139, 0.5882500738453962],
 [0.7570821537162007, 0.7576445993512019, 0.7570007300282396],
 [1.022582311321646, 1.0225040939257053, 1.0225132989851697],
 [1.0456745834279195, 1.0455146220948277, 1.0455334466015351],
 [133, 133, 133],
 [38, 38, 38],
 [8, 8, 8],
 [3, 3, 3],
 0.002304553985595703,
 0.00128173828125)

Lasso Regression

# Importing Lasso package from sklearn.linear_model
from sklearn.linear_model import Lasso

modelname = 'LassoRegression'
pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(Lasso(), x_train, y_train, x_test)
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

This is quite bad than Multiple Linear Regression. Too many records giving error more than 3.0

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

The prediction is not good. We have to tune or avoid this Lasso Algorithm.

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

The Lasso Algorithm not properly learned the training set itself. That's why the prection is bad.

This Lasso model is not considered for final evaluation because both learning and prediction are poor when fitted with default parameters of Lasso Regressor. We can check the performance of the model after tuning some of the parameters.

Hyper-parameter Tuning on Lasso Regression

modelname = 'LassoRegression Tuned'
pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(Lasso(alpha = 0.1, selection = 'random'), x_train, y_train, x_test)
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

Here, we adjusted the aplha value from 1.0 to 0.01. Setting alpha as zero means that linear regression and it is not advised. So, here we chosen smaller alpha value of 0.01. And, Setting selection as 'random' often leads to significantly faster convergence. So we set 'random' for 'selection' parameter.

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

After changing some of the parameters, we got the predictions closer to the blue line. The predictions are good and looks like output from Multiple Linear Regression. Most important is that we have to check whether the model is overfitted with training data or not !!!

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

From the above plot we confirm that the model is not overfitted with training data. So, we can consider this model for final evaluation. From the above graphs we noticed that the tuning improves learning and predictions.

recorddata(modelname, pred_y_test, y_test, zero_to_one, one_to_two, two_to_three, greater_than_three, trn_time, pred_time)
model_name, r2_score_, mae,rmse,mse,error_0_to_1, error_1_to_2, error_2_to_3, error_greater_than_3, trn_time, pred_time

(['MultipleLinearRegression',
  'RidgeRegression',
  'RidgeRegression Tuned',
  'LassoRegression Tuned'],
 [0.5881944916179406,
  0.5882574872756139,
  0.5882500738453962,
  0.5195868929852978],
 [0.7570821537162007,
  0.7576445993512019,
  0.7570007300282396,
  0.839614296475421],
 [1.022582311321646,
  1.0225040939257053,
  1.0225132989851697,
  1.1044844964051186],
 [1.0456745834279195,
  1.0455146220948277,
  1.0455334466015351,
  1.2198860027992684],
 [133, 133, 133, 126],
 [38, 38, 38, 44],
 [8, 8, 8, 7],
 [3, 3, 3, 5],
 0.0024209022521972656,
 0.0005033016204833984)

Random Forest Regressor

# Importing RandomForestRegressor from sklearn.ensemble
from sklearn.ensemble import RandomForestRegressor

modelname = 'RandomForestRegressor'
pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(RandomForestRegressor(), x_train, y_train, x_test)
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

From the above scatter plot, we can see that most of the plots ranges between 0 and 1. Some of the values inbetween 1 and 2, few of them inbetween 2 and 3. Only few points which is greater than 3.0

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

RandomForestRegressor is good at prediction. At the same time, we have to check whether the model is overfitted with training set or not.

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

From, the above graph, we can say that the predictions are on and around prefectline. Here, most of the predictions are around the perfectline. So, we can't say this as overfitted on training set. At the same time, we have look at the the performance on test data. In that, only few points are away from the perfectline. So, we can't consider this as overfitted model. We can consider this for final evaluation.

recorddata(modelname, pred_y_test, y_test, zero_to_one, one_to_two, two_to_three, greater_than_three, trn_time, pred_time)
model_name, r2_score_, mae,rmse,mse,error_0_to_1, error_1_to_2, error_2_to_3, error_greater_than_3, trn_time, pred_time

(['MultipleLinearRegression',
  'RidgeRegression',
  'RidgeRegression Tuned',
  'LassoRegression Tuned',
  'RandomForestRegressor'],
 [0.5881944916179406,
  0.5882574872756139,
  0.5882500738453962,
  0.5195868929852978,
  0.6459987684820476],
 [0.7570821537162007,
  0.7576445993512019,
  0.7570007300282396,
  0.839614296475421,
  0.6889759568590751],
 [1.022582311321646,
  1.0225040939257053,
  1.0225132989851697,
  1.1044844964051186,
  0.9481009607961802],
 [1.0456745834279195,
  1.0455146220948277,
  1.0455334466015351,
  1.2198860027992684,
  0.8988954318626401],
 [133, 133, 133, 126, 139],
 [38, 38, 38, 44, 33],
 [8, 8, 8, 7, 9],
 [3, 3, 3, 5, 1],
 0.17950201034545898,
 0.008001327514648438)

Hyper-parameter Tuning on RandomForestRegressor

modelname = 'RandomForestRegressor Tuned'
pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(RandomForestRegressor(min_samples_split=15, min_samples_leaf=10, max_depth=10), x_train, y_train, x_test)
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

The predictions are good. Only one point which is too far away from perfect line.

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

From the above scatter plot the predictions are on the perfect line as well as around the perfect line. So, this is not a overfitted model. But, this is quite bad in learning as well as in predictions of RandomForestRegressor with default parameters. We can consider this for final evaluation.

recorddata(modelname, pred_y_test, y_test, zero_to_one, one_to_two, two_to_three, greater_than_three, trn_time, pred_time)
model_name, r2_score_, mae,rmse,mse,error_0_to_1, error_1_to_2, error_2_to_3, error_greater_than_3, trn_time, pred_time

(['MultipleLinearRegression',
  'RidgeRegression',
  'RidgeRegression Tuned',
  'LassoRegression Tuned',
  'RandomForestRegressor',
  'RandomForestRegressor Tuned'],
 [0.5881944916179406,
  0.5882574872756139,
  0.5882500738453962,
  0.5195868929852978,
  0.6459987684820476,
  0.6115841548371949],
 [0.7570821537162007,
  0.7576445993512019,
  0.7570007300282396,
  0.839614296475421,
  0.6889759568590751,
  0.7237713897549489],
 [1.022582311321646,
  1.0225040939257053,
  1.0225132989851697,
  1.1044844964051186,
  0.9481009607961802,
  0.9931175792144878],
 [1.0456745834279195,
  1.0455146220948277,
  1.0455334466015351,
  1.2198860027992684,
  0.8988954318626401,
  0.9862825261448445],
 [133, 133, 133, 126, 139, 132],
 [38, 38, 38, 44, 33, 40],
 [8, 8, 8, 7, 9, 8],
 [3, 3, 3, 5, 1, 2],
 0.1291055679321289,
 0.006001472473144531)

SVR(Support Vector Regressor)

# Importing SupportVectorRegressor(SVR) from sklearn.svm
from sklearn.svm import SVR

modelname = 'SupportVectorRegressor'
pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(SVR(), x_train, y_train, x_test)
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

The predictions are good, only one data given an error greater than 3.0

Further we have to check with visualization on both training and testing set.

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

From the above scatter plot, we can see that the predictions are on and around the perfect line. Only one point that is far away from perfect line.

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

From the avove scatter plot we confirm that the model is not overfitted on training data. We can consider this model for final evaluation.

We got generalized model with default parameters. So, hyper-parameter tuning not done on SVR

recorddata(modelname, pred_y_test, y_test, zero_to_one, one_to_two, two_to_three, greater_than_three, trn_time, pred_time)
model_name, r2_score_, mae,rmse,mse,error_0_to_1, error_1_to_2, error_2_to_3, error_greater_than_3, trn_time, pred_time

(['MultipleLinearRegression',
  'RidgeRegression',
  'RidgeRegression Tuned',
  'LassoRegression Tuned',
  'RandomForestRegressor',
  'RandomForestRegressor Tuned',
  'SupportVectorRegressor'],
 [0.5881944916179406,
  0.5882574872756139,
  0.5882500738453962,
  0.5195868929852978,
  0.6459987684820476,
  0.6115841548371949,
  0.6091219882096025],
 [0.7570821537162007,
  0.7576445993512019,
  0.7570007300282396,
  0.839614296475421,
  0.6889759568590751,
  0.7237713897549489,
  0.7249561882292098],
 [1.022582311321646,
  1.0225040939257053,
  1.0225132989851697,
  1.1044844964051186,
  0.9481009607961802,
  0.9931175792144878,
  0.9962602910310709],
 [1.0456745834279195,
  1.0455146220948277,
  1.0455334466015351,
  1.2198860027992684,
  0.8988954318626401,
  0.9862825261448445,
  0.9925345674853142],
 [133, 133, 133, 126, 139, 132, 138],
 [38, 38, 38, 44, 33, 40, 28],
 [8, 8, 8, 7, 9, 8, 13],
 [3, 3, 3, 5, 1, 2, 3],
 0.023469924926757812,
 0.008001565933227539)

KNeighborsRegressor

# Importing KNeighborsRegressor from sklearn.neighbors
from sklearn.neighbors import KNeighborsRegressor

# Choosing optimal 'K' value
knr_errors = []
for i in range(2,50):
    knr = KNeighborsRegressor(n_neighbors=i)
    knr.fit(x_train, y_train)
    pred_knr = knr.predict(x_test)
    error = []
    for j in range(0,len(x_test)):
        err = pred_knr[j] - list(y_test)[j]
        error.append(abs(err))
    knr_errors.append(np.mean(error))

# Line plot shows from which k value the errors are stable.
plx.line(knr_errors)

The Error is stable between the 'k' value of 6 and 10. So we can choose k value as 8.

modelname = 'KNeighborsRegressor'
pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(KNeighborsRegressor(n_neighbors=8), x_train, y_train, x_test)
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

The above scatter plot shows the goodness of the prediction.

kNeighborsRegressor is good at prediction. We have to check whether the model is overfitted with training data or not !!!

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

From the above scatter plot we confirm that the model is not overfitted with the training data. And we can consider this model for final evaluation.

recorddata(modelname, pred_y_test, y_test, zero_to_one, one_to_two, two_to_three, greater_than_three, trn_time, pred_time)
model_name, r2_score_, mae,rmse,mse,error_0_to_1, error_1_to_2, error_2_to_3, error_greater_than_3, trn_time, pred_time

(['MultipleLinearRegression',
  'RidgeRegression',
  'RidgeRegression Tuned',
  'LassoRegression Tuned',
  'RandomForestRegressor',
  'RandomForestRegressor Tuned',
  'SupportVectorRegressor',
  'KNeighborsRegressor'],
 [0.5881944916179406,
  0.5882574872756139,
  0.5882500738453962,
  0.5195868929852978,
  0.6459987684820476,
  0.6115841548371949,
  0.6091219882096025,
  0.5950797047642148],
 [0.7570821537162007,
  0.7576445993512019,
  0.7570007300282396,
  0.839614296475421,
  0.6889759568590751,
  0.7237713897549489,
  0.7249561882292098,
  0.732286401098901],
 [1.022582311321646,
  1.0225040939257053,
  1.0225132989851697,
  1.1044844964051186,
  0.9481009607961802,
  0.9931175792144878,
  0.9962602910310709,
  1.013997706429134],
 [1.0456745834279195,
  1.0455146220948277,
  1.0455334466015351,
  1.2198860027992684,
  0.8988954318626401,
  0.9862825261448445,
  0.9925345674853142,
  1.028191348643544],
 [133, 133, 133, 126, 139, 132, 138, 135],
 [38, 38, 38, 44, 33, 40, 28, 34],
 [8, 8, 8, 7, 9, 8, 13, 10],
 [3, 3, 3, 5, 1, 2, 3, 3],
 0.0024039745330810547,
 0.00212860107421875)

XGBoost

# Importing XGBRegressor from xgboost
from xgboost import XGBRegressor

modelname = 'XGBRegressor'
pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(XGBRegressor(), x_train, y_train, x_test)
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

Most of values lies in bettween 0 and 1, Some of the values inbetween 1 and 2 and few of them greater than 2.

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

Most of the red markers lies around the blue line(perfectline). So, this will be good model. At the same time we have to check whether the model is overfitted on training set or not !!!

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

Yes, the model is highly overfitted on training set. We have to fine tune the model by changing the values in some of the parameters of XGBRegressor.

Hyper-parameter Tuning on XGBRegressor

modelname = 'XGBRegressor Tuned'
pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(XGBRegressor(n_estimators = 12, max_depth = 7), x_train, y_train, x_test)
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

This model looks good in error rate. Let's check the performance on both training and testing data.

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

The predictions are good.

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

This looks better than the model of XGBRegressor with default parameters. XGBRegressor is quite unstable while changing the parameter 'n_estimators' which is nothing but the Number of Gradient boosted trees. So, we're not going to consider XGBRegressor model for final evaluation.

GradientBoostingRegressor

from sklearn.ensemble import GradientBoostingRegressor, AdaBoostRegressor

modelname = 'GradientBoosting Regressor'
pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(GradientBoostingRegressor(), x_train, y_train, x_test)
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

Most of the error is ranges between 0 and 1

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

From the above scatter plot, we know that predictions are on and around the perfect line.

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

From the above scatter plot, we confirm that the model is not overfitted on the training set.

recorddata(modelname, pred_y_test, y_test, zero_to_one, one_to_two, two_to_three, greater_than_three, trn_time, pred_time)
model_name, r2_score_, mae,rmse,mse,error_0_to_1, error_1_to_2, error_2_to_3, error_greater_than_3, trn_time, pred_time

(['MultipleLinearRegression',
  'RidgeRegression',
  'RidgeRegression Tuned',
  'LassoRegression Tuned',
  'RandomForestRegressor',
  'RandomForestRegressor Tuned',
  'SupportVectorRegressor',
  'KNeighborsRegressor',
  'GradientBoosting Regressor'],
 [0.5881944916179406,
  0.5882574872756139,
  0.5882500738453962,
  0.5195868929852978,
  0.6459987684820476,
  0.6115841548371949,
  0.6091219882096025,
  0.5950797047642148,
  0.6562976891201446],
 [0.7570821537162007,
  0.7576445993512019,
  0.7570007300282396,
  0.839614296475421,
  0.6889759568590751,
  0.7237713897549489,
  0.7249561882292098,
  0.732286401098901,
  0.6931135058778565],
 [1.022582311321646,
  1.0225040939257053,
  1.0225132989851697,
  1.1044844964051186,
  0.9481009607961802,
  0.9931175792144878,
  0.9962602910310709,
  1.013997706429134,
  0.9342076650826047],
 [1.0456745834279195,
  1.0455146220948277,
  1.0455334466015351,
  1.2198860027992684,
  0.8988954318626401,
  0.9862825261448445,
  0.9925345674853142,
  1.028191348643544,
  0.872743961499092],
 [133, 133, 133, 126, 139, 132, 138, 135, 136],
 [38, 38, 38, 44, 33, 40, 28, 34, 36],
 [8, 8, 8, 7, 9, 8, 13, 10, 9],
 [3, 3, 3, 5, 1, 2, 3, 3, 1],
 0.7602193355560303,
 0.01300191879272461)

AdaBoostRegressor

modelname = 'AdaBoostRegressor Tuned'
pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(AdaBoostRegressor(), x_train, y_train, x_test)
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

From the above scatter plot, we know that the model is unstable.

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

This model is unstable. So, this is not considered.

CatBoostRegressor

from catboost import CatBoostRegressor

modelname = 'CatBoostRegressor'
pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(CatBoostRegressor(), x_train, y_train, x_test)
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

Learning rate set to 0.038915
0:	learn: 1.3950462	total: 183ms	remaining: 3m 2s
1:	learn: 1.3696513	total: 194ms	remaining: 1m 36s
2:	learn: 1.3462533	total: 204ms	remaining: 1m 7s
3:	learn: 1.3228517	total: 212ms	remaining: 52.9s
4:	learn: 1.3007950	total: 221ms	remaining: 43.9s
5:	learn: 1.2802232	total: 230ms	remaining: 38.1s
6:	learn: 1.2594330	total: 239ms	remaining: 33.9s
7:	learn: 1.2403990	total: 248ms	remaining: 30.8s
8:	learn: 1.2246075	total: 255ms	remaining: 28s
9:	learn: 1.2061130	total: 264ms	remaining: 26.1s
10:	learn: 1.1902095	total: 273ms	remaining: 24.5s
11:	learn: 1.1736182	total: 282ms	remaining: 23.2s
12:	learn: 1.1605399	total: 292ms	remaining: 22.2s
13:	learn: 1.1452195	total: 301ms	remaining: 21.2s
14:	learn: 1.1311825	total: 310ms	remaining: 20.4s
15:	learn: 1.1168671	total: 320ms	remaining: 19.7s
16:	learn: 1.1020656	total: 329ms	remaining: 19s
17:	learn: 1.0890027	total: 338ms	remaining: 18.5s
18:	learn: 1.0762744	total: 347ms	remaining: 17.9s
19:	learn: 1.0673066	total: 356ms	remaining: 17.5s
20:	learn: 1.0570495	total: 365ms	remaining: 17s
21:	learn: 1.0454440	total: 375ms	remaining: 16.7s
22:	learn: 1.0361226	total: 385ms	remaining: 16.4s
23:	learn: 1.0247689	total: 394ms	remaining: 16s
24:	learn: 1.0162311	total: 403ms	remaining: 15.7s
25:	learn: 1.0060790	total: 412ms	remaining: 15.4s
26:	learn: 0.9988028	total: 421ms	remaining: 15.2s
27:	learn: 0.9898959	total: 431ms	remaining: 15s
28:	learn: 0.9819677	total: 439ms	remaining: 14.7s
29:	learn: 0.9722318	total: 448ms	remaining: 14.5s
30:	learn: 0.9653898	total: 457ms	remaining: 14.3s
31:	learn: 0.9584767	total: 466ms	remaining: 14.1s
32:	learn: 0.9525708	total: 474ms	remaining: 13.9s
33:	learn: 0.9460462	total: 483ms	remaining: 13.7s
34:	learn: 0.9388596	total: 492ms	remaining: 13.6s
35:	learn: 0.9348293	total: 498ms	remaining: 13.3s
36:	learn: 0.9288253	total: 507ms	remaining: 13.2s
37:	learn: 0.9237843	total: 515ms	remaining: 13s
38:	learn: 0.9189675	total: 520ms	remaining: 12.8s
39:	learn: 0.9134715	total: 529ms	remaining: 12.7s
40:	learn: 0.9084961	total: 538ms	remaining: 12.6s
41:	learn: 0.9035085	total: 546ms	remaining: 12.5s
42:	learn: 0.8976850	total: 555ms	remaining: 12.4s
43:	learn: 0.8926826	total: 564ms	remaining: 12.3s
44:	learn: 0.8882163	total: 576ms	remaining: 12.2s
45:	learn: 0.8840302	total: 587ms	remaining: 12.2s
46:	learn: 0.8798324	total: 596ms	remaining: 12.1s
47:	learn: 0.8749891	total: 605ms	remaining: 12s
48:	learn: 0.8706214	total: 614ms	remaining: 11.9s
49:	learn: 0.8652792	total: 623ms	remaining: 11.8s
50:	learn: 0.8620398	total: 631ms	remaining: 11.7s
51:	learn: 0.8577681	total: 640ms	remaining: 11.7s
52:	learn: 0.8532664	total: 648ms	remaining: 11.6s
53:	learn: 0.8489425	total: 657ms	remaining: 11.5s
54:	learn: 0.8455853	total: 665ms	remaining: 11.4s
55:	learn: 0.8423713	total: 674ms	remaining: 11.4s
56:	learn: 0.8394469	total: 682ms	remaining: 11.3s
57:	learn: 0.8362318	total: 691ms	remaining: 11.2s
58:	learn: 0.8321098	total: 699ms	remaining: 11.2s
59:	learn: 0.8291747	total: 708ms	remaining: 11.1s
60:	learn: 0.8267261	total: 714ms	remaining: 11s
61:	learn: 0.8242080	total: 723ms	remaining: 10.9s
62:	learn: 0.8214943	total: 733ms	remaining: 10.9s
63:	learn: 0.8197312	total: 741ms	remaining: 10.8s
64:	learn: 0.8173187	total: 750ms	remaining: 10.8s
65:	learn: 0.8143466	total: 759ms	remaining: 10.7s
66:	learn: 0.8121863	total: 770ms	remaining: 10.7s
67:	learn: 0.8099483	total: 778ms	remaining: 10.7s
68:	learn: 0.8080163	total: 787ms	remaining: 10.6s
69:	learn: 0.8056393	total: 795ms	remaining: 10.6s
70:	learn: 0.8035744	total: 805ms	remaining: 10.5s
71:	learn: 0.8016071	total: 813ms	remaining: 10.5s
72:	learn: 0.7995764	total: 822ms	remaining: 10.4s
73:	learn: 0.7972110	total: 830ms	remaining: 10.4s
74:	learn: 0.7946534	total: 840ms	remaining: 10.4s
75:	learn: 0.7927409	total: 849ms	remaining: 10.3s
76:	learn: 0.7902009	total: 858ms	remaining: 10.3s
77:	learn: 0.7884775	total: 867ms	remaining: 10.2s
78:	learn: 0.7863217	total: 877ms	remaining: 10.2s
79:	learn: 0.7844628	total: 885ms	remaining: 10.2s
80:	learn: 0.7824856	total: 895ms	remaining: 10.1s
81:	learn: 0.7817941	total: 904ms	remaining: 10.1s
82:	learn: 0.7799301	total: 913ms	remaining: 10.1s
83:	learn: 0.7787568	total: 923ms	remaining: 10.1s
84:	learn: 0.7777198	total: 929ms	remaining: 10s
85:	learn: 0.7752601	total: 938ms	remaining: 9.97s
86:	learn: 0.7740591	total: 949ms	remaining: 9.96s
87:	learn: 0.7723314	total: 959ms	remaining: 9.94s
88:	learn: 0.7708867	total: 968ms	remaining: 9.91s
89:	learn: 0.7688186	total: 977ms	remaining: 9.88s
90:	learn: 0.7680792	total: 986ms	remaining: 9.85s
91:	learn: 0.7669149	total: 994ms	remaining: 9.81s
92:	learn: 0.7646524	total: 1s	remaining: 9.78s
93:	learn: 0.7629020	total: 1.01s	remaining: 9.74s
94:	learn: 0.7610001	total: 1.02s	remaining: 9.72s
95:	learn: 0.7592402	total: 1.03s	remaining: 9.69s
96:	learn: 0.7578142	total: 1.04s	remaining: 9.65s
97:	learn: 0.7560559	total: 1.04s	remaining: 9.62s
98:	learn: 0.7533382	total: 1.05s	remaining: 9.59s
99:	learn: 0.7521387	total: 1.06s	remaining: 9.57s
100:	learn: 0.7514729	total: 1.07s	remaining: 9.51s
101:	learn: 0.7506308	total: 1.08s	remaining: 9.48s
102:	learn: 0.7497653	total: 1.08s	remaining: 9.45s
103:	learn: 0.7479599	total: 1.09s	remaining: 9.43s
104:	learn: 0.7474751	total: 1.1s	remaining: 9.4s
105:	learn: 0.7467257	total: 1.11s	remaining: 9.37s
106:	learn: 0.7453102	total: 1.12s	remaining: 9.34s
107:	learn: 0.7443463	total: 1.13s	remaining: 9.32s
108:	learn: 0.7430576	total: 1.14s	remaining: 9.3s
109:	learn: 0.7419409	total: 1.15s	remaining: 9.29s
110:	learn: 0.7413300	total: 1.16s	remaining: 9.29s
111:	learn: 0.7406001	total: 1.17s	remaining: 9.26s
112:	learn: 0.7400707	total: 1.18s	remaining: 9.24s
113:	learn: 0.7389722	total: 1.19s	remaining: 9.22s
114:	learn: 0.7375542	total: 1.2s	remaining: 9.2s
115:	learn: 0.7368091	total: 1.2s	remaining: 9.18s
116:	learn: 0.7353959	total: 1.21s	remaining: 9.15s
117:	learn: 0.7349776	total: 1.22s	remaining: 9.13s
118:	learn: 0.7344631	total: 1.23s	remaining: 9.11s
119:	learn: 0.7334034	total: 1.24s	remaining: 9.09s
120:	learn: 0.7321619	total: 1.25s	remaining: 9.07s
121:	learn: 0.7303557	total: 1.26s	remaining: 9.04s
122:	learn: 0.7287877	total: 1.26s	remaining: 9.02s
123:	learn: 0.7273264	total: 1.27s	remaining: 9s
124:	learn: 0.7267199	total: 1.28s	remaining: 8.98s
125:	learn: 0.7260575	total: 1.29s	remaining: 8.96s
126:	learn: 0.7252300	total: 1.3s	remaining: 8.94s
127:	learn: 0.7238924	total: 1.31s	remaining: 8.92s
128:	learn: 0.7222956	total: 1.32s	remaining: 8.91s
129:	learn: 0.7215773	total: 1.33s	remaining: 8.89s
130:	learn: 0.7203846	total: 1.34s	remaining: 8.87s
131:	learn: 0.7196453	total: 1.35s	remaining: 8.87s
132:	learn: 0.7188172	total: 1.36s	remaining: 8.86s
133:	learn: 0.7180887	total: 1.37s	remaining: 8.84s
134:	learn: 0.7177733	total: 1.38s	remaining: 8.82s
135:	learn: 0.7168422	total: 1.38s	remaining: 8.8s
136:	learn: 0.7161121	total: 1.39s	remaining: 8.78s
137:	learn: 0.7151778	total: 1.4s	remaining: 8.76s
138:	learn: 0.7147659	total: 1.41s	remaining: 8.74s
139:	learn: 0.7143746	total: 1.42s	remaining: 8.72s
140:	learn: 0.7128790	total: 1.43s	remaining: 8.71s
141:	learn: 0.7119977	total: 1.44s	remaining: 8.69s
142:	learn: 0.7109791	total: 1.45s	remaining: 8.67s
143:	learn: 0.7098466	total: 1.45s	remaining: 8.64s
144:	learn: 0.7092226	total: 1.46s	remaining: 8.62s
145:	learn: 0.7086454	total: 1.47s	remaining: 8.6s
146:	learn: 0.7075577	total: 1.48s	remaining: 8.59s
147:	learn: 0.7071614	total: 1.49s	remaining: 8.55s
148:	learn: 0.7061947	total: 1.49s	remaining: 8.54s
149:	learn: 0.7045789	total: 1.5s	remaining: 8.52s
150:	learn: 0.7042107	total: 1.51s	remaining: 8.5s
151:	learn: 0.7035220	total: 1.52s	remaining: 8.48s
152:	learn: 0.7028232	total: 1.53s	remaining: 8.47s
153:	learn: 0.7021225	total: 1.54s	remaining: 8.45s
154:	learn: 0.7011405	total: 1.55s	remaining: 8.44s
155:	learn: 0.6995598	total: 1.56s	remaining: 8.44s
156:	learn: 0.6986213	total: 1.57s	remaining: 8.43s
157:	learn: 0.6980160	total: 1.58s	remaining: 8.41s
158:	learn: 0.6969697	total: 1.59s	remaining: 8.4s
159:	learn: 0.6960005	total: 1.6s	remaining: 8.39s
160:	learn: 0.6947610	total: 1.61s	remaining: 8.38s
161:	learn: 0.6939912	total: 1.62s	remaining: 8.38s
162:	learn: 0.6931996	total: 1.63s	remaining: 8.37s
163:	learn: 0.6922730	total: 1.64s	remaining: 8.37s
164:	learn: 0.6912940	total: 1.65s	remaining: 8.36s
165:	learn: 0.6910287	total: 1.66s	remaining: 8.35s
166:	learn: 0.6903397	total: 1.67s	remaining: 8.33s
167:	learn: 0.6894965	total: 1.68s	remaining: 8.32s
168:	learn: 0.6890487	total: 1.69s	remaining: 8.31s
169:	learn: 0.6880418	total: 1.7s	remaining: 8.3s
170:	learn: 0.6873436	total: 1.71s	remaining: 8.29s
171:	learn: 0.6869019	total: 1.72s	remaining: 8.28s
172:	learn: 0.6862580	total: 1.73s	remaining: 8.27s
173:	learn: 0.6853864	total: 1.74s	remaining: 8.26s
174:	learn: 0.6847296	total: 1.75s	remaining: 8.25s
175:	learn: 0.6842037	total: 1.76s	remaining: 8.24s
176:	learn: 0.6829445	total: 1.77s	remaining: 8.23s
177:	learn: 0.6824552	total: 1.78s	remaining: 8.22s
178:	learn: 0.6822191	total: 1.79s	remaining: 8.2s
179:	learn: 0.6814881	total: 1.8s	remaining: 8.19s
180:	learn: 0.6811267	total: 1.81s	remaining: 8.18s
181:	learn: 0.6809645	total: 1.82s	remaining: 8.16s
182:	learn: 0.6805649	total: 1.83s	remaining: 8.15s
183:	learn: 0.6803766	total: 1.84s	remaining: 8.14s
184:	learn: 0.6790119	total: 1.85s	remaining: 8.13s
185:	learn: 0.6786665	total: 1.85s	remaining: 8.12s
186:	learn: 0.6783870	total: 1.86s	remaining: 8.11s
187:	learn: 0.6781656	total: 1.87s	remaining: 8.09s
188:	learn: 0.6777593	total: 1.88s	remaining: 8.08s
189:	learn: 0.6764404	total: 1.89s	remaining: 8.07s
190:	learn: 0.6761084	total: 1.9s	remaining: 8.05s
191:	learn: 0.6755413	total: 1.91s	remaining: 8.04s
192:	learn: 0.6749866	total: 1.92s	remaining: 8.03s
193:	learn: 0.6739333	total: 1.93s	remaining: 8.01s
194:	learn: 0.6733202	total: 1.94s	remaining: 8s
195:	learn: 0.6726264	total: 1.95s	remaining: 7.99s
196:	learn: 0.6720084	total: 1.96s	remaining: 7.98s
197:	learn: 0.6713212	total: 1.97s	remaining: 7.97s
198:	learn: 0.6711555	total: 1.98s	remaining: 7.96s
199:	learn: 0.6706822	total: 1.99s	remaining: 7.94s
200:	learn: 0.6700853	total: 2s	remaining: 7.93s
201:	learn: 0.6694728	total: 2s	remaining: 7.92s
202:	learn: 0.6688673	total: 2.01s	remaining: 7.9s
203:	learn: 0.6687383	total: 2.02s	remaining: 7.89s
204:	learn: 0.6683736	total: 2.03s	remaining: 7.88s
205:	learn: 0.6680518	total: 2.04s	remaining: 7.86s
206:	learn: 0.6674924	total: 2.05s	remaining: 7.85s
207:	learn: 0.6671784	total: 2.06s	remaining: 7.84s
208:	learn: 0.6658242	total: 2.07s	remaining: 7.83s
209:	learn: 0.6654192	total: 2.08s	remaining: 7.82s
210:	learn: 0.6641059	total: 2.09s	remaining: 7.8s
211:	learn: 0.6630689	total: 2.1s	remaining: 7.79s
212:	learn: 0.6616457	total: 2.1s	remaining: 7.78s
213:	learn: 0.6613279	total: 2.12s	remaining: 7.77s
214:	learn: 0.6610280	total: 2.12s	remaining: 7.76s
215:	learn: 0.6608251	total: 2.13s	remaining: 7.75s
216:	learn: 0.6605145	total: 2.15s	remaining: 7.74s
217:	learn: 0.6599509	total: 2.16s	remaining: 7.74s
218:	learn: 0.6594302	total: 2.17s	remaining: 7.72s
219:	learn: 0.6592059	total: 2.17s	remaining: 7.71s
220:	learn: 0.6582336	total: 2.18s	remaining: 7.69s
221:	learn: 0.6572189	total: 2.19s	remaining: 7.68s
222:	learn: 0.6567477	total: 2.2s	remaining: 7.67s
223:	learn: 0.6565006	total: 2.21s	remaining: 7.66s
224:	learn: 0.6559340	total: 2.22s	remaining: 7.65s
225:	learn: 0.6554117	total: 2.23s	remaining: 7.64s
226:	learn: 0.6550570	total: 2.24s	remaining: 7.63s
227:	learn: 0.6547720	total: 2.25s	remaining: 7.62s
228:	learn: 0.6545223	total: 2.26s	remaining: 7.61s
229:	learn: 0.6543275	total: 2.27s	remaining: 7.59s
230:	learn: 0.6541271	total: 2.28s	remaining: 7.58s
231:	learn: 0.6532797	total: 2.29s	remaining: 7.57s
232:	learn: 0.6527653	total: 2.29s	remaining: 7.56s
233:	learn: 0.6518704	total: 2.3s	remaining: 7.54s
234:	learn: 0.6509120	total: 2.31s	remaining: 7.53s
235:	learn: 0.6505354	total: 2.32s	remaining: 7.52s
236:	learn: 0.6503937	total: 2.33s	remaining: 7.51s
237:	learn: 0.6501922	total: 2.34s	remaining: 7.5s
238:	learn: 0.6499838	total: 2.35s	remaining: 7.49s
239:	learn: 0.6492967	total: 2.36s	remaining: 7.48s
240:	learn: 0.6484505	total: 2.37s	remaining: 7.47s
241:	learn: 0.6475037	total: 2.38s	remaining: 7.46s
242:	learn: 0.6467785	total: 2.39s	remaining: 7.45s
243:	learn: 0.6463238	total: 2.4s	remaining: 7.44s
244:	learn: 0.6457631	total: 2.41s	remaining: 7.43s
245:	learn: 0.6454996	total: 2.42s	remaining: 7.42s
246:	learn: 0.6453370	total: 2.43s	remaining: 7.4s
247:	learn: 0.6450759	total: 2.44s	remaining: 7.39s
248:	learn: 0.6448223	total: 2.45s	remaining: 7.38s
249:	learn: 0.6440405	total: 2.46s	remaining: 7.37s
250:	learn: 0.6438385	total: 2.46s	remaining: 7.35s
251:	learn: 0.6437582	total: 2.47s	remaining: 7.34s
252:	learn: 0.6431104	total: 2.48s	remaining: 7.33s
253:	learn: 0.6424098	total: 2.49s	remaining: 7.32s
254:	learn: 0.6421425	total: 2.5s	remaining: 7.31s
255:	learn: 0.6415452	total: 2.51s	remaining: 7.3s
256:	learn: 0.6410047	total: 2.52s	remaining: 7.29s
257:	learn: 0.6397056	total: 2.53s	remaining: 7.28s
258:	learn: 0.6395583	total: 2.54s	remaining: 7.27s
259:	learn: 0.6389959	total: 2.55s	remaining: 7.26s
260:	learn: 0.6381515	total: 2.56s	remaining: 7.25s
261:	learn: 0.6377236	total: 2.57s	remaining: 7.24s
262:	learn: 0.6374108	total: 2.58s	remaining: 7.22s
263:	learn: 0.6372927	total: 2.58s	remaining: 7.2s
264:	learn: 0.6371209	total: 2.59s	remaining: 7.19s
265:	learn: 0.6369714	total: 2.6s	remaining: 7.18s
266:	learn: 0.6367381	total: 2.61s	remaining: 7.16s
267:	learn: 0.6362422	total: 2.62s	remaining: 7.15s
268:	learn: 0.6353104	total: 2.63s	remaining: 7.14s
269:	learn: 0.6348220	total: 2.64s	remaining: 7.13s
270:	learn: 0.6346902	total: 2.65s	remaining: 7.12s
271:	learn: 0.6345911	total: 2.65s	remaining: 7.1s
272:	learn: 0.6343180	total: 2.66s	remaining: 7.09s
273:	learn: 0.6334031	total: 2.67s	remaining: 7.07s
274:	learn: 0.6327112	total: 2.68s	remaining: 7.06s
275:	learn: 0.6315637	total: 2.69s	remaining: 7.05s
276:	learn: 0.6312954	total: 2.7s	remaining: 7.04s
277:	learn: 0.6307014	total: 2.7s	remaining: 7.03s
278:	learn: 0.6301423	total: 2.71s	remaining: 7.01s
279:	learn: 0.6295587	total: 2.72s	remaining: 7s
280:	learn: 0.6285288	total: 2.73s	remaining: 6.99s
281:	learn: 0.6277225	total: 2.74s	remaining: 6.99s
282:	learn: 0.6268288	total: 2.75s	remaining: 6.97s
283:	learn: 0.6266897	total: 2.76s	remaining: 6.96s
284:	learn: 0.6261720	total: 2.77s	remaining: 6.95s
285:	learn: 0.6260572	total: 2.78s	remaining: 6.94s
286:	learn: 0.6245935	total: 2.79s	remaining: 6.94s
287:	learn: 0.6242503	total: 2.8s	remaining: 6.93s
288:	learn: 0.6238902	total: 2.81s	remaining: 6.92s
289:	learn: 0.6233669	total: 2.82s	remaining: 6.91s
290:	learn: 0.6232558	total: 2.83s	remaining: 6.89s
291:	learn: 0.6230555	total: 2.84s	remaining: 6.88s
292:	learn: 0.6223064	total: 2.85s	remaining: 6.87s
293:	learn: 0.6212931	total: 2.86s	remaining: 6.86s
294:	learn: 0.6202967	total: 2.87s	remaining: 6.85s
295:	learn: 0.6194403	total: 2.88s	remaining: 6.84s
296:	learn: 0.6192205	total: 2.89s	remaining: 6.83s
297:	learn: 0.6190440	total: 2.9s	remaining: 6.82s
298:	learn: 0.6188079	total: 2.9s	remaining: 6.81s
299:	learn: 0.6180780	total: 2.91s	remaining: 6.8s
300:	learn: 0.6178202	total: 2.92s	remaining: 6.79s
301:	learn: 0.6176180	total: 2.93s	remaining: 6.78s
302:	learn: 0.6164944	total: 2.94s	remaining: 6.78s
303:	learn: 0.6160978	total: 2.96s	remaining: 6.77s
304:	learn: 0.6156733	total: 2.96s	remaining: 6.75s
305:	learn: 0.6152233	total: 2.97s	remaining: 6.75s
306:	learn: 0.6140203	total: 2.98s	remaining: 6.73s
307:	learn: 0.6133141	total: 2.98s	remaining: 6.7s
308:	learn: 0.6123019	total: 2.98s	remaining: 6.67s
309:	learn: 0.6113666	total: 2.98s	remaining: 6.64s
310:	learn: 0.6112819	total: 2.98s	remaining: 6.61s
311:	learn: 0.6108148	total: 2.98s	remaining: 6.58s
312:	learn: 0.6105833	total: 2.98s	remaining: 6.55s
313:	learn: 0.6095566	total: 2.99s	remaining: 6.52s
314:	learn: 0.6094560	total: 2.99s	remaining: 6.5s
315:	learn: 0.6090208	total: 2.99s	remaining: 6.47s
316:	learn: 0.6087143	total: 2.99s	remaining: 6.44s
317:	learn: 0.6080963	total: 2.99s	remaining: 6.41s
318:	learn: 0.6080002	total: 2.99s	remaining: 6.38s
319:	learn: 0.6077586	total: 2.99s	remaining: 6.36s
320:	learn: 0.6070930	total: 2.99s	remaining: 6.33s
321:	learn: 0.6066421	total: 2.99s	remaining: 6.3s
322:	learn: 0.6057883	total: 2.99s	remaining: 6.27s
323:	learn: 0.6050517	total: 2.99s	remaining: 6.25s
324:	learn: 0.6048315	total: 2.99s	remaining: 6.22s
325:	learn: 0.6040709	total: 3s	remaining: 6.19s
326:	learn: 0.6039251	total: 3s	remaining: 6.17s
327:	learn: 0.6038563	total: 3s	remaining: 6.14s
328:	learn: 0.6028080	total: 3s	remaining: 6.11s
329:	learn: 0.6021370	total: 3s	remaining: 6.09s
330:	learn: 0.6019703	total: 3s	remaining: 6.06s
331:	learn: 0.6011323	total: 3s	remaining: 6.04s
332:	learn: 0.6005946	total: 3s	remaining: 6.01s
333:	learn: 0.5993203	total: 3s	remaining: 5.99s
334:	learn: 0.5988085	total: 3s	remaining: 5.96s
335:	learn: 0.5978980	total: 3s	remaining: 5.93s
336:	learn: 0.5975652	total: 3s	remaining: 5.91s
337:	learn: 0.5975023	total: 3s	remaining: 5.88s
338:	learn: 0.5964797	total: 3s	remaining: 5.86s
339:	learn: 0.5953157	total: 3.01s	remaining: 5.84s
340:	learn: 0.5952457	total: 3.01s	remaining: 5.81s
341:	learn: 0.5950066	total: 3.01s	remaining: 5.79s
342:	learn: 0.5947275	total: 3.01s	remaining: 5.76s
343:	learn: 0.5937038	total: 3.01s	remaining: 5.74s
344:	learn: 0.5934775	total: 3.01s	remaining: 5.72s
345:	learn: 0.5933811	total: 3.01s	remaining: 5.69s
346:	learn: 0.5927573	total: 3.01s	remaining: 5.67s
347:	learn: 0.5926358	total: 3.01s	remaining: 5.64s
348:	learn: 0.5916712	total: 3.01s	remaining: 5.62s
349:	learn: 0.5905840	total: 3.01s	remaining: 5.6s
350:	learn: 0.5901915	total: 3.02s	remaining: 5.58s
351:	learn: 0.5895047	total: 3.02s	remaining: 5.55s
352:	learn: 0.5885408	total: 3.02s	remaining: 5.53s
353:	learn: 0.5876765	total: 3.02s	remaining: 5.51s
354:	learn: 0.5874439	total: 3.02s	remaining: 5.49s
355:	learn: 0.5863500	total: 3.02s	remaining: 5.46s
356:	learn: 0.5859486	total: 3.02s	remaining: 5.44s
357:	learn: 0.5847679	total: 3.02s	remaining: 5.42s
358:	learn: 0.5839094	total: 3.02s	remaining: 5.4s
359:	learn: 0.5833119	total: 3.02s	remaining: 5.37s
360:	learn: 0.5828578	total: 3.02s	remaining: 5.35s
361:	learn: 0.5818744	total: 3.02s	remaining: 5.33s
362:	learn: 0.5807398	total: 3.02s	remaining: 5.31s
363:	learn: 0.5805181	total: 3.03s	remaining: 5.29s
364:	learn: 0.5795183	total: 3.03s	remaining: 5.27s
365:	learn: 0.5789582	total: 3.03s	remaining: 5.25s
366:	learn: 0.5778332	total: 3.03s	remaining: 5.22s
367:	learn: 0.5776866	total: 3.03s	remaining: 5.2s
368:	learn: 0.5771186	total: 3.03s	remaining: 5.18s
369:	learn: 0.5764771	total: 3.03s	remaining: 5.16s
370:	learn: 0.5760303	total: 3.03s	remaining: 5.14s
371:	learn: 0.5757108	total: 3.03s	remaining: 5.12s
372:	learn: 0.5751045	total: 3.03s	remaining: 5.1s
373:	learn: 0.5741921	total: 3.04s	remaining: 5.08s
374:	learn: 0.5740176	total: 3.04s	remaining: 5.06s
375:	learn: 0.5737061	total: 3.04s	remaining: 5.04s
376:	learn: 0.5730039	total: 3.04s	remaining: 5.02s
377:	learn: 0.5728608	total: 3.04s	remaining: 5s
378:	learn: 0.5724377	total: 3.04s	remaining: 4.98s
379:	learn: 0.5719131	total: 3.04s	remaining: 4.96s
380:	learn: 0.5717644	total: 3.04s	remaining: 4.94s
381:	learn: 0.5713488	total: 3.04s	remaining: 4.92s
382:	learn: 0.5710830	total: 3.04s	remaining: 4.9s
383:	learn: 0.5708448	total: 3.04s	remaining: 4.88s
384:	learn: 0.5706358	total: 3.04s	remaining: 4.86s
385:	learn: 0.5704782	total: 3.04s	remaining: 4.84s
386:	learn: 0.5697220	total: 3.04s	remaining: 4.82s
387:	learn: 0.5694011	total: 3.05s	remaining: 4.8s
388:	learn: 0.5687586	total: 3.05s	remaining: 4.79s
389:	learn: 0.5684650	total: 3.05s	remaining: 4.77s
390:	learn: 0.5683913	total: 3.05s	remaining: 4.75s
391:	learn: 0.5674477	total: 3.05s	remaining: 4.73s
392:	learn: 0.5662967	total: 3.05s	remaining: 4.71s
393:	learn: 0.5661533	total: 3.05s	remaining: 4.69s
394:	learn: 0.5658122	total: 3.05s	remaining: 4.67s
395:	learn: 0.5649596	total: 3.05s	remaining: 4.66s
396:	learn: 0.5643723	total: 3.05s	remaining: 4.64s
397:	learn: 0.5638675	total: 3.05s	remaining: 4.62s
398:	learn: 0.5634269	total: 3.06s	remaining: 4.6s
399:	learn: 0.5627076	total: 3.06s	remaining: 4.58s
400:	learn: 0.5617660	total: 3.06s	remaining: 4.57s
401:	learn: 0.5610281	total: 3.06s	remaining: 4.55s
402:	learn: 0.5605920	total: 3.06s	remaining: 4.53s
403:	learn: 0.5601052	total: 3.06s	remaining: 4.51s
404:	learn: 0.5592174	total: 3.06s	remaining: 4.5s
405:	learn: 0.5584193	total: 3.06s	remaining: 4.48s
406:	learn: 0.5577234	total: 3.06s	remaining: 4.46s
407:	learn: 0.5573829	total: 3.06s	remaining: 4.44s
408:	learn: 0.5569708	total: 3.06s	remaining: 4.43s
409:	learn: 0.5567368	total: 3.06s	remaining: 4.41s
410:	learn: 0.5560715	total: 3.06s	remaining: 4.39s
411:	learn: 0.5553059	total: 3.07s	remaining: 4.38s
412:	learn: 0.5550806	total: 3.07s	remaining: 4.36s
413:	learn: 0.5545208	total: 3.07s	remaining: 4.34s
414:	learn: 0.5539181	total: 3.07s	remaining: 4.33s
415:	learn: 0.5537511	total: 3.07s	remaining: 4.31s
416:	learn: 0.5532977	total: 3.07s	remaining: 4.29s
417:	learn: 0.5531465	total: 3.07s	remaining: 4.28s
418:	learn: 0.5524242	total: 3.07s	remaining: 4.26s
419:	learn: 0.5520901	total: 3.07s	remaining: 4.24s
420:	learn: 0.5515968	total: 3.07s	remaining: 4.23s
421:	learn: 0.5513128	total: 3.07s	remaining: 4.21s
422:	learn: 0.5511453	total: 3.08s	remaining: 4.2s
423:	learn: 0.5508648	total: 3.08s	remaining: 4.18s
424:	learn: 0.5498649	total: 3.08s	remaining: 4.16s
425:	learn: 0.5486718	total: 3.08s	remaining: 4.15s
426:	learn: 0.5486261	total: 3.08s	remaining: 4.13s
427:	learn: 0.5483964	total: 3.08s	remaining: 4.12s
428:	learn: 0.5475943	total: 3.08s	remaining: 4.1s
429:	learn: 0.5470049	total: 3.08s	remaining: 4.08s
430:	learn: 0.5464966	total: 3.08s	remaining: 4.07s
431:	learn: 0.5453797	total: 3.08s	remaining: 4.05s
432:	learn: 0.5449161	total: 3.08s	remaining: 4.04s
433:	learn: 0.5447032	total: 3.08s	remaining: 4.02s
434:	learn: 0.5440389	total: 3.09s	remaining: 4.01s
435:	learn: 0.5432027	total: 3.09s	remaining: 3.99s
436:	learn: 0.5430412	total: 3.09s	remaining: 3.98s
437:	learn: 0.5423188	total: 3.09s	remaining: 3.96s
438:	learn: 0.5418470	total: 3.09s	remaining: 3.95s
439:	learn: 0.5417726	total: 3.09s	remaining: 3.93s
440:	learn: 0.5409265	total: 3.09s	remaining: 3.92s
441:	learn: 0.5401634	total: 3.09s	remaining: 3.9s
442:	learn: 0.5400509	total: 3.09s	remaining: 3.89s
443:	learn: 0.5396050	total: 3.09s	remaining: 3.87s
444:	learn: 0.5387438	total: 3.1s	remaining: 3.86s
445:	learn: 0.5379454	total: 3.1s	remaining: 3.85s
446:	learn: 0.5375378	total: 3.1s	remaining: 3.83s
447:	learn: 0.5373777	total: 3.1s	remaining: 3.82s
448:	learn: 0.5369699	total: 3.1s	remaining: 3.8s
449:	learn: 0.5368446	total: 3.1s	remaining: 3.79s
450:	learn: 0.5366639	total: 3.1s	remaining: 3.77s
451:	learn: 0.5365707	total: 3.1s	remaining: 3.76s
452:	learn: 0.5360174	total: 3.1s	remaining: 3.75s
453:	learn: 0.5354091	total: 3.1s	remaining: 3.73s
454:	learn: 0.5350592	total: 3.1s	remaining: 3.72s
455:	learn: 0.5349635	total: 3.1s	remaining: 3.7s
456:	learn: 0.5341392	total: 3.1s	remaining: 3.69s
457:	learn: 0.5341018	total: 3.11s	remaining: 3.68s
458:	learn: 0.5338701	total: 3.11s	remaining: 3.66s
459:	learn: 0.5332920	total: 3.11s	remaining: 3.65s
460:	learn: 0.5331891	total: 3.11s	remaining: 3.63s
461:	learn: 0.5325212	total: 3.11s	remaining: 3.62s
462:	learn: 0.5317435	total: 3.11s	remaining: 3.61s
463:	learn: 0.5310108	total: 3.11s	remaining: 3.59s
464:	learn: 0.5301131	total: 3.11s	remaining: 3.58s
465:	learn: 0.5298396	total: 3.11s	remaining: 3.57s
466:	learn: 0.5292289	total: 3.11s	remaining: 3.55s
467:	learn: 0.5287558	total: 3.12s	remaining: 3.54s
468:	learn: 0.5282110	total: 3.12s	remaining: 3.53s
469:	learn: 0.5275874	total: 3.12s	remaining: 3.52s
470:	learn: 0.5269288	total: 3.12s	remaining: 3.5s
471:	learn: 0.5266450	total: 3.12s	remaining: 3.49s
472:	learn: 0.5258312	total: 3.12s	remaining: 3.48s
473:	learn: 0.5254065	total: 3.12s	remaining: 3.46s
474:	learn: 0.5244777	total: 3.12s	remaining: 3.45s
475:	learn: 0.5236259	total: 3.12s	remaining: 3.44s
476:	learn: 0.5230440	total: 3.12s	remaining: 3.42s
477:	learn: 0.5225121	total: 3.12s	remaining: 3.41s
478:	learn: 0.5219097	total: 3.13s	remaining: 3.4s
479:	learn: 0.5213021	total: 3.13s	remaining: 3.39s
480:	learn: 0.5210137	total: 3.13s	remaining: 3.37s
481:	learn: 0.5209084	total: 3.13s	remaining: 3.36s
482:	learn: 0.5201569	total: 3.13s	remaining: 3.35s
483:	learn: 0.5195415	total: 3.13s	remaining: 3.34s
484:	learn: 0.5188309	total: 3.13s	remaining: 3.32s
485:	learn: 0.5181506	total: 3.13s	remaining: 3.31s
486:	learn: 0.5175557	total: 3.13s	remaining: 3.3s
487:	learn: 0.5169718	total: 3.13s	remaining: 3.29s
488:	learn: 0.5162189	total: 3.13s	remaining: 3.27s
489:	learn: 0.5155668	total: 3.13s	remaining: 3.26s
490:	learn: 0.5149721	total: 3.14s	remaining: 3.25s
491:	learn: 0.5145393	total: 3.14s	remaining: 3.24s
492:	learn: 0.5138298	total: 3.14s	remaining: 3.23s
493:	learn: 0.5136922	total: 3.14s	remaining: 3.21s
494:	learn: 0.5133192	total: 3.14s	remaining: 3.2s
495:	learn: 0.5130017	total: 3.14s	remaining: 3.19s
496:	learn: 0.5124926	total: 3.14s	remaining: 3.18s
497:	learn: 0.5123014	total: 3.14s	remaining: 3.17s
498:	learn: 0.5117071	total: 3.14s	remaining: 3.16s
499:	learn: 0.5109924	total: 3.14s	remaining: 3.14s
500:	learn: 0.5102873	total: 3.15s	remaining: 3.13s
501:	learn: 0.5101680	total: 3.15s	remaining: 3.12s
502:	learn: 0.5100803	total: 3.15s	remaining: 3.11s
503:	learn: 0.5094356	total: 3.15s	remaining: 3.1s
504:	learn: 0.5093297	total: 3.15s	remaining: 3.09s
505:	learn: 0.5092658	total: 3.15s	remaining: 3.08s
506:	learn: 0.5086881	total: 3.15s	remaining: 3.06s
507:	learn: 0.5083195	total: 3.15s	remaining: 3.05s
508:	learn: 0.5079218	total: 3.15s	remaining: 3.04s
509:	learn: 0.5076072	total: 3.15s	remaining: 3.03s
510:	learn: 0.5073857	total: 3.15s	remaining: 3.02s
511:	learn: 0.5067729	total: 3.15s	remaining: 3.01s
512:	learn: 0.5061413	total: 3.16s	remaining: 3s
513:	learn: 0.5052899	total: 3.16s	remaining: 2.98s
514:	learn: 0.5052063	total: 3.16s	remaining: 2.97s
515:	learn: 0.5051735	total: 3.16s	remaining: 2.96s
516:	learn: 0.5050616	total: 3.16s	remaining: 2.95s
517:	learn: 0.5048912	total: 3.16s	remaining: 2.94s
518:	learn: 0.5041102	total: 3.16s	remaining: 2.93s
519:	learn: 0.5034733	total: 3.16s	remaining: 2.92s
520:	learn: 0.5029285	total: 3.16s	remaining: 2.91s
521:	learn: 0.5026644	total: 3.16s	remaining: 2.9s
522:	learn: 0.5024526	total: 3.16s	remaining: 2.89s
523:	learn: 0.5023621	total: 3.17s	remaining: 2.88s
524:	learn: 0.5020114	total: 3.17s	remaining: 2.87s
525:	learn: 0.5014167	total: 3.17s	remaining: 2.85s
526:	learn: 0.5010994	total: 3.17s	remaining: 2.84s
527:	learn: 0.5003902	total: 3.17s	remaining: 2.83s
528:	learn: 0.5000493	total: 3.17s	remaining: 2.82s
529:	learn: 0.4993099	total: 3.17s	remaining: 2.81s
530:	learn: 0.4986533	total: 3.17s	remaining: 2.8s
531:	learn: 0.4980941	total: 3.17s	remaining: 2.79s
532:	learn: 0.4976070	total: 3.17s	remaining: 2.78s
533:	learn: 0.4969983	total: 3.17s	remaining: 2.77s
534:	learn: 0.4966175	total: 3.17s	remaining: 2.76s
535:	learn: 0.4960936	total: 3.18s	remaining: 2.75s
536:	learn: 0.4955477	total: 3.18s	remaining: 2.74s
537:	learn: 0.4949224	total: 3.18s	remaining: 2.73s
538:	learn: 0.4945934	total: 3.18s	remaining: 2.72s
539:	learn: 0.4941449	total: 3.18s	remaining: 2.71s
540:	learn: 0.4940387	total: 3.18s	remaining: 2.7s
541:	learn: 0.4936570	total: 3.18s	remaining: 2.69s
542:	learn: 0.4930024	total: 3.18s	remaining: 2.68s
543:	learn: 0.4924550	total: 3.18s	remaining: 2.67s
544:	learn: 0.4922505	total: 3.18s	remaining: 2.66s
545:	learn: 0.4918125	total: 3.19s	remaining: 2.65s
546:	learn: 0.4912844	total: 3.19s	remaining: 2.64s
547:	learn: 0.4907931	total: 3.19s	remaining: 2.63s
548:	learn: 0.4903635	total: 3.19s	remaining: 2.62s
549:	learn: 0.4898001	total: 3.19s	remaining: 2.61s
550:	learn: 0.4893046	total: 3.19s	remaining: 2.6s
551:	learn: 0.4887435	total: 3.19s	remaining: 2.59s
552:	learn: 0.4886887	total: 3.19s	remaining: 2.58s
553:	learn: 0.4880563	total: 3.19s	remaining: 2.57s
554:	learn: 0.4874305	total: 3.19s	remaining: 2.56s
555:	learn: 0.4872179	total: 3.19s	remaining: 2.55s
556:	learn: 0.4868572	total: 3.19s	remaining: 2.54s
557:	learn: 0.4863393	total: 3.2s	remaining: 2.53s
558:	learn: 0.4857351	total: 3.2s	remaining: 2.52s
559:	learn: 0.4856088	total: 3.2s	remaining: 2.51s
560:	learn: 0.4854242	total: 3.2s	remaining: 2.5s
561:	learn: 0.4847588	total: 3.2s	remaining: 2.49s
562:	learn: 0.4845813	total: 3.2s	remaining: 2.48s
563:	learn: 0.4838921	total: 3.2s	remaining: 2.47s
564:	learn: 0.4831296	total: 3.2s	remaining: 2.46s
565:	learn: 0.4827536	total: 3.2s	remaining: 2.46s
566:	learn: 0.4824093	total: 3.2s	remaining: 2.45s
567:	learn: 0.4823485	total: 3.2s	remaining: 2.44s
568:	learn: 0.4817392	total: 3.21s	remaining: 2.43s
569:	learn: 0.4812722	total: 3.21s	remaining: 2.42s
570:	learn: 0.4811859	total: 3.21s	remaining: 2.41s
571:	learn: 0.4809864	total: 3.21s	remaining: 2.4s
572:	learn: 0.4809616	total: 3.21s	remaining: 2.39s
573:	learn: 0.4808709	total: 3.21s	remaining: 2.38s
574:	learn: 0.4803060	total: 3.21s	remaining: 2.37s
575:	learn: 0.4802644	total: 3.21s	remaining: 2.36s
576:	learn: 0.4799497	total: 3.21s	remaining: 2.35s
577:	learn: 0.4793763	total: 3.21s	remaining: 2.35s
578:	learn: 0.4790842	total: 3.21s	remaining: 2.34s
579:	learn: 0.4790345	total: 3.21s	remaining: 2.33s
580:	learn: 0.4786272	total: 3.22s	remaining: 2.32s
581:	learn: 0.4785694	total: 3.22s	remaining: 2.31s
582:	learn: 0.4780670	total: 3.22s	remaining: 2.3s
583:	learn: 0.4774669	total: 3.22s	remaining: 2.29s
584:	learn: 0.4770404	total: 3.22s	remaining: 2.28s
585:	learn: 0.4765158	total: 3.22s	remaining: 2.27s
586:	learn: 0.4761938	total: 3.22s	remaining: 2.27s
587:	learn: 0.4759633	total: 3.22s	remaining: 2.26s
588:	learn: 0.4753750	total: 3.22s	remaining: 2.25s
589:	learn: 0.4750258	total: 3.22s	remaining: 2.24s
590:	learn: 0.4741125	total: 3.23s	remaining: 2.23s
591:	learn: 0.4736890	total: 3.23s	remaining: 2.22s
592:	learn: 0.4732919	total: 3.23s	remaining: 2.21s
593:	learn: 0.4726432	total: 3.23s	remaining: 2.21s
594:	learn: 0.4721483	total: 3.23s	remaining: 2.2s
595:	learn: 0.4719962	total: 3.23s	remaining: 2.19s
596:	learn: 0.4714680	total: 3.23s	remaining: 2.18s
597:	learn: 0.4710310	total: 3.23s	remaining: 2.17s
598:	learn: 0.4705232	total: 3.23s	remaining: 2.16s
599:	learn: 0.4705053	total: 3.23s	remaining: 2.15s
600:	learn: 0.4699287	total: 3.23s	remaining: 2.15s
601:	learn: 0.4694456	total: 3.23s	remaining: 2.14s
602:	learn: 0.4693778	total: 3.23s	remaining: 2.13s
603:	learn: 0.4691358	total: 3.24s	remaining: 2.12s
604:	learn: 0.4690317	total: 3.24s	remaining: 2.11s
605:	learn: 0.4685659	total: 3.24s	remaining: 2.1s
606:	learn: 0.4682942	total: 3.24s	remaining: 2.1s
607:	learn: 0.4677877	total: 3.24s	remaining: 2.09s
608:	learn: 0.4674257	total: 3.24s	remaining: 2.08s
609:	learn: 0.4673231	total: 3.24s	remaining: 2.07s
610:	learn: 0.4670449	total: 3.24s	remaining: 2.06s
611:	learn: 0.4665659	total: 3.24s	remaining: 2.06s
612:	learn: 0.4664796	total: 3.24s	remaining: 2.05s
613:	learn: 0.4659513	total: 3.25s	remaining: 2.04s
614:	learn: 0.4654248	total: 3.25s	remaining: 2.03s
615:	learn: 0.4653721	total: 3.25s	remaining: 2.02s
616:	learn: 0.4653377	total: 3.25s	remaining: 2.02s
617:	learn: 0.4648911	total: 3.25s	remaining: 2.01s
618:	learn: 0.4647392	total: 3.25s	remaining: 2s
619:	learn: 0.4643642	total: 3.25s	remaining: 1.99s
620:	learn: 0.4639003	total: 3.25s	remaining: 1.98s
621:	learn: 0.4637388	total: 3.25s	remaining: 1.98s
622:	learn: 0.4637081	total: 3.25s	remaining: 1.97s
623:	learn: 0.4636597	total: 3.25s	remaining: 1.96s
624:	learn: 0.4633374	total: 3.25s	remaining: 1.95s
625:	learn: 0.4629267	total: 3.26s	remaining: 1.95s
626:	learn: 0.4624722	total: 3.26s	remaining: 1.94s
627:	learn: 0.4621251	total: 3.26s	remaining: 1.93s
628:	learn: 0.4615837	total: 3.26s	remaining: 1.92s
629:	learn: 0.4615515	total: 3.26s	remaining: 1.91s
630:	learn: 0.4611055	total: 3.26s	remaining: 1.91s
631:	learn: 0.4610057	total: 3.26s	remaining: 1.9s
632:	learn: 0.4603388	total: 3.26s	remaining: 1.89s
633:	learn: 0.4602484	total: 3.26s	remaining: 1.88s
634:	learn: 0.4601428	total: 3.26s	remaining: 1.88s
635:	learn: 0.4597444	total: 3.26s	remaining: 1.87s
636:	learn: 0.4592472	total: 3.27s	remaining: 1.86s
637:	learn: 0.4591733	total: 3.27s	remaining: 1.85s
638:	learn: 0.4586800	total: 3.27s	remaining: 1.85s
639:	learn: 0.4581956	total: 3.27s	remaining: 1.84s
640:	learn: 0.4581092	total: 3.27s	remaining: 1.83s
641:	learn: 0.4575203	total: 3.27s	remaining: 1.82s
642:	learn: 0.4570819	total: 3.27s	remaining: 1.82s
643:	learn: 0.4568423	total: 3.27s	remaining: 1.81s
644:	learn: 0.4565154	total: 3.27s	remaining: 1.8s
645:	learn: 0.4561394	total: 3.27s	remaining: 1.79s
646:	learn: 0.4557075	total: 3.27s	remaining: 1.79s
647:	learn: 0.4553049	total: 3.27s	remaining: 1.78s
648:	learn: 0.4549117	total: 3.28s	remaining: 1.77s
649:	learn: 0.4545814	total: 3.28s	remaining: 1.76s
650:	learn: 0.4539277	total: 3.28s	remaining: 1.76s
651:	learn: 0.4535354	total: 3.28s	remaining: 1.75s
652:	learn: 0.4531751	total: 3.28s	remaining: 1.74s
653:	learn: 0.4527442	total: 3.28s	remaining: 1.74s
654:	learn: 0.4523037	total: 3.28s	remaining: 1.73s
655:	learn: 0.4519321	total: 3.28s	remaining: 1.72s
656:	learn: 0.4515090	total: 3.28s	remaining: 1.71s
657:	learn: 0.4514777	total: 3.28s	remaining: 1.71s
658:	learn: 0.4513567	total: 3.29s	remaining: 1.7s
659:	learn: 0.4512243	total: 3.29s	remaining: 1.69s
660:	learn: 0.4508144	total: 3.29s	remaining: 1.69s
661:	learn: 0.4506330	total: 3.29s	remaining: 1.68s
662:	learn: 0.4502802	total: 3.29s	remaining: 1.67s
663:	learn: 0.4499707	total: 3.29s	remaining: 1.66s
664:	learn: 0.4495331	total: 3.29s	remaining: 1.66s
665:	learn: 0.4491345	total: 3.29s	remaining: 1.65s
666:	learn: 0.4489186	total: 3.29s	remaining: 1.64s
667:	learn: 0.4488733	total: 3.29s	remaining: 1.64s
668:	learn: 0.4482734	total: 3.29s	remaining: 1.63s
669:	learn: 0.4478755	total: 3.29s	remaining: 1.62s
670:	learn: 0.4475891	total: 3.3s	remaining: 1.62s
671:	learn: 0.4475132	total: 3.3s	remaining: 1.61s
672:	learn: 0.4470651	total: 3.3s	remaining: 1.6s
673:	learn: 0.4469712	total: 3.3s	remaining: 1.59s
674:	learn: 0.4469441	total: 3.3s	remaining: 1.59s
675:	learn: 0.4463541	total: 3.3s	remaining: 1.58s
676:	learn: 0.4462092	total: 3.3s	remaining: 1.57s
677:	learn: 0.4457038	total: 3.3s	remaining: 1.57s
678:	learn: 0.4452393	total: 3.3s	remaining: 1.56s
679:	learn: 0.4448930	total: 3.3s	remaining: 1.55s
680:	learn: 0.4448040	total: 3.31s	remaining: 1.55s
681:	learn: 0.4446160	total: 3.31s	remaining: 1.54s
682:	learn: 0.4441778	total: 3.31s	remaining: 1.53s
683:	learn: 0.4441692	total: 3.31s	remaining: 1.53s
684:	learn: 0.4438265	total: 3.31s	remaining: 1.52s
685:	learn: 0.4434331	total: 3.31s	remaining: 1.51s
686:	learn: 0.4431354	total: 3.31s	remaining: 1.51s
687:	learn: 0.4427572	total: 3.31s	remaining: 1.5s
688:	learn: 0.4422730	total: 3.31s	remaining: 1.5s
689:	learn: 0.4422641	total: 3.31s	remaining: 1.49s
690:	learn: 0.4420618	total: 3.31s	remaining: 1.48s
691:	learn: 0.4417409	total: 3.31s	remaining: 1.48s
692:	learn: 0.4412265	total: 3.31s	remaining: 1.47s
693:	learn: 0.4408198	total: 3.32s	remaining: 1.46s
694:	learn: 0.4404484	total: 3.32s	remaining: 1.46s
695:	learn: 0.4399815	total: 3.32s	remaining: 1.45s
696:	learn: 0.4399621	total: 3.32s	remaining: 1.44s
697:	learn: 0.4393897	total: 3.32s	remaining: 1.44s
698:	learn: 0.4391457	total: 3.32s	remaining: 1.43s
699:	learn: 0.4388376	total: 3.32s	remaining: 1.42s
700:	learn: 0.4388206	total: 3.32s	remaining: 1.42s
701:	learn: 0.4386588	total: 3.32s	remaining: 1.41s
702:	learn: 0.4383463	total: 3.33s	remaining: 1.4s
703:	learn: 0.4378407	total: 3.33s	remaining: 1.4s
704:	learn: 0.4376171	total: 3.33s	remaining: 1.39s
705:	learn: 0.4373328	total: 3.33s	remaining: 1.39s
706:	learn: 0.4372471	total: 3.33s	remaining: 1.38s
707:	learn: 0.4369125	total: 3.33s	remaining: 1.37s
708:	learn: 0.4366733	total: 3.33s	remaining: 1.37s
709:	learn: 0.4365744	total: 3.33s	remaining: 1.36s
710:	learn: 0.4363609	total: 3.33s	remaining: 1.35s
711:	learn: 0.4359354	total: 3.33s	remaining: 1.35s
712:	learn: 0.4357479	total: 3.33s	remaining: 1.34s
713:	learn: 0.4351403	total: 3.33s	remaining: 1.33s
714:	learn: 0.4350739	total: 3.33s	remaining: 1.33s
715:	learn: 0.4349234	total: 3.34s	remaining: 1.32s
716:	learn: 0.4346503	total: 3.34s	remaining: 1.32s
717:	learn: 0.4343456	total: 3.34s	remaining: 1.31s
718:	learn: 0.4338917	total: 3.34s	remaining: 1.3s
719:	learn: 0.4337750	total: 3.34s	remaining: 1.3s
720:	learn: 0.4332737	total: 3.34s	remaining: 1.29s
721:	learn: 0.4328949	total: 3.34s	remaining: 1.29s
722:	learn: 0.4324809	total: 3.34s	remaining: 1.28s
723:	learn: 0.4320934	total: 3.34s	remaining: 1.27s
724:	learn: 0.4314443	total: 3.35s	remaining: 1.27s
725:	learn: 0.4311057	total: 3.35s	remaining: 1.26s
726:	learn: 0.4308830	total: 3.35s	remaining: 1.26s
727:	learn: 0.4304835	total: 3.35s	remaining: 1.25s
728:	learn: 0.4301326	total: 3.35s	remaining: 1.24s
729:	learn: 0.4298160	total: 3.35s	remaining: 1.24s
730:	learn: 0.4295606	total: 3.35s	remaining: 1.23s
731:	learn: 0.4294899	total: 3.35s	remaining: 1.23s
732:	learn: 0.4290775	total: 3.35s	remaining: 1.22s
733:	learn: 0.4287648	total: 3.35s	remaining: 1.22s
734:	learn: 0.4283388	total: 3.35s	remaining: 1.21s
735:	learn: 0.4280635	total: 3.35s	remaining: 1.2s
736:	learn: 0.4278368	total: 3.36s	remaining: 1.2s
737:	learn: 0.4274989	total: 3.36s	remaining: 1.19s
738:	learn: 0.4272491	total: 3.36s	remaining: 1.19s
739:	learn: 0.4268147	total: 3.36s	remaining: 1.18s
740:	learn: 0.4266685	total: 3.36s	remaining: 1.17s
741:	learn: 0.4262155	total: 3.36s	remaining: 1.17s
742:	learn: 0.4258810	total: 3.36s	remaining: 1.16s
743:	learn: 0.4254880	total: 3.36s	remaining: 1.16s
744:	learn: 0.4252201	total: 3.36s	remaining: 1.15s
745:	learn: 0.4251413	total: 3.36s	remaining: 1.15s
746:	learn: 0.4249222	total: 3.37s	remaining: 1.14s
747:	learn: 0.4246194	total: 3.37s	remaining: 1.13s
748:	learn: 0.4245839	total: 3.37s	remaining: 1.13s
749:	learn: 0.4242724	total: 3.37s	remaining: 1.12s
750:	learn: 0.4239454	total: 3.37s	remaining: 1.12s
751:	learn: 0.4235045	total: 3.37s	remaining: 1.11s
752:	learn: 0.4232867	total: 3.37s	remaining: 1.1s
753:	learn: 0.4230122	total: 3.37s	remaining: 1.1s
754:	learn: 0.4227669	total: 3.37s	remaining: 1.09s
755:	learn: 0.4223467	total: 3.37s	remaining: 1.09s
756:	learn: 0.4220053	total: 3.37s	remaining: 1.08s
757:	learn: 0.4216778	total: 3.38s	remaining: 1.08s
758:	learn: 0.4214359	total: 3.38s	remaining: 1.07s
759:	learn: 0.4207841	total: 3.38s	remaining: 1.07s
760:	learn: 0.4207648	total: 3.38s	remaining: 1.06s
761:	learn: 0.4204616	total: 3.38s	remaining: 1.05s
762:	learn: 0.4203913	total: 3.38s	remaining: 1.05s
763:	learn: 0.4200424	total: 3.38s	remaining: 1.04s
764:	learn: 0.4198055	total: 3.38s	remaining: 1.04s
765:	learn: 0.4197941	total: 3.38s	remaining: 1.03s
766:	learn: 0.4196835	total: 3.38s	remaining: 1.03s
767:	learn: 0.4195891	total: 3.38s	remaining: 1.02s
768:	learn: 0.4192916	total: 3.38s	remaining: 1.02s
769:	learn: 0.4188102	total: 3.38s	remaining: 1.01s
770:	learn: 0.4184233	total: 3.39s	remaining: 1s
771:	learn: 0.4181661	total: 3.39s	remaining: 1s
772:	learn: 0.4179490	total: 3.39s	remaining: 995ms
773:	learn: 0.4174713	total: 3.39s	remaining: 990ms
774:	learn: 0.4169179	total: 3.39s	remaining: 984ms
775:	learn: 0.4166305	total: 3.39s	remaining: 979ms
776:	learn: 0.4161963	total: 3.39s	remaining: 973ms
777:	learn: 0.4161831	total: 3.39s	remaining: 968ms
778:	learn: 0.4159114	total: 3.39s	remaining: 963ms
779:	learn: 0.4157426	total: 3.39s	remaining: 957ms
780:	learn: 0.4156102	total: 3.4s	remaining: 952ms
781:	learn: 0.4152987	total: 3.4s	remaining: 947ms
782:	learn: 0.4149897	total: 3.4s	remaining: 941ms
783:	learn: 0.4147345	total: 3.4s	remaining: 936ms
784:	learn: 0.4144792	total: 3.4s	remaining: 931ms
785:	learn: 0.4142213	total: 3.4s	remaining: 926ms
786:	learn: 0.4139097	total: 3.4s	remaining: 920ms
787:	learn: 0.4138772	total: 3.4s	remaining: 915ms
788:	learn: 0.4136368	total: 3.4s	remaining: 910ms
789:	learn: 0.4133774	total: 3.4s	remaining: 905ms
790:	learn: 0.4131660	total: 3.4s	remaining: 899ms
791:	learn: 0.4125935	total: 3.4s	remaining: 894ms
792:	learn: 0.4123901	total: 3.4s	remaining: 889ms
793:	learn: 0.4119357	total: 3.41s	remaining: 884ms
794:	learn: 0.4116441	total: 3.41s	remaining: 879ms
795:	learn: 0.4114411	total: 3.41s	remaining: 873ms
796:	learn: 0.4110923	total: 3.41s	remaining: 868ms
797:	learn: 0.4109099	total: 3.41s	remaining: 863ms
798:	learn: 0.4104297	total: 3.41s	remaining: 858ms
799:	learn: 0.4101135	total: 3.41s	remaining: 853ms
800:	learn: 0.4097188	total: 3.41s	remaining: 848ms
801:	learn: 0.4096901	total: 3.41s	remaining: 843ms
802:	learn: 0.4094731	total: 3.41s	remaining: 838ms
803:	learn: 0.4090131	total: 3.42s	remaining: 833ms
804:	learn: 0.4084535	total: 3.42s	remaining: 828ms
805:	learn: 0.4083610	total: 3.42s	remaining: 823ms
806:	learn: 0.4082562	total: 3.42s	remaining: 818ms
807:	learn: 0.4082076	total: 3.42s	remaining: 812ms
808:	learn: 0.4078685	total: 3.42s	remaining: 807ms
809:	learn: 0.4077210	total: 3.42s	remaining: 802ms
810:	learn: 0.4075890	total: 3.42s	remaining: 797ms
811:	learn: 0.4074536	total: 3.42s	remaining: 792ms
812:	learn: 0.4070811	total: 3.42s	remaining: 787ms
813:	learn: 0.4068615	total: 3.42s	remaining: 783ms
814:	learn: 0.4066725	total: 3.42s	remaining: 778ms
815:	learn: 0.4062024	total: 3.43s	remaining: 773ms
816:	learn: 0.4059626	total: 3.43s	remaining: 768ms
817:	learn: 0.4056921	total: 3.43s	remaining: 763ms
818:	learn: 0.4054753	total: 3.43s	remaining: 758ms
819:	learn: 0.4053142	total: 3.43s	remaining: 753ms
820:	learn: 0.4049526	total: 3.43s	remaining: 748ms
821:	learn: 0.4045893	total: 3.43s	remaining: 743ms
822:	learn: 0.4043024	total: 3.43s	remaining: 738ms
823:	learn: 0.4041633	total: 3.43s	remaining: 733ms
824:	learn: 0.4038104	total: 3.43s	remaining: 729ms
825:	learn: 0.4033883	total: 3.44s	remaining: 724ms
826:	learn: 0.4030713	total: 3.44s	remaining: 719ms
827:	learn: 0.4025499	total: 3.44s	remaining: 714ms
828:	learn: 0.4022392	total: 3.44s	remaining: 709ms
829:	learn: 0.4022178	total: 3.44s	remaining: 704ms
830:	learn: 0.4018945	total: 3.44s	remaining: 700ms
831:	learn: 0.4014665	total: 3.44s	remaining: 695ms
832:	learn: 0.4010831	total: 3.44s	remaining: 690ms
833:	learn: 0.4007993	total: 3.44s	remaining: 685ms
834:	learn: 0.4006404	total: 3.44s	remaining: 681ms
835:	learn: 0.4004281	total: 3.44s	remaining: 676ms
836:	learn: 0.4003109	total: 3.44s	remaining: 671ms
837:	learn: 0.4001459	total: 3.45s	remaining: 666ms
838:	learn: 0.3996928	total: 3.45s	remaining: 662ms
839:	learn: 0.3995075	total: 3.45s	remaining: 657ms
840:	learn: 0.3990880	total: 3.45s	remaining: 652ms
841:	learn: 0.3988086	total: 3.45s	remaining: 647ms
842:	learn: 0.3984170	total: 3.45s	remaining: 643ms
843:	learn: 0.3982086	total: 3.45s	remaining: 638ms
844:	learn: 0.3980515	total: 3.45s	remaining: 633ms
845:	learn: 0.3978379	total: 3.45s	remaining: 629ms
846:	learn: 0.3971947	total: 3.45s	remaining: 624ms
847:	learn: 0.3970013	total: 3.46s	remaining: 619ms
848:	learn: 0.3966088	total: 3.46s	remaining: 615ms
849:	learn: 0.3962744	total: 3.46s	remaining: 610ms
850:	learn: 0.3959668	total: 3.46s	remaining: 605ms
851:	learn: 0.3956837	total: 3.46s	remaining: 601ms
852:	learn: 0.3954026	total: 3.46s	remaining: 596ms
853:	learn: 0.3952358	total: 3.46s	remaining: 592ms
854:	learn: 0.3949489	total: 3.46s	remaining: 587ms
855:	learn: 0.3947295	total: 3.46s	remaining: 582ms
856:	learn: 0.3946800	total: 3.46s	remaining: 578ms
857:	learn: 0.3944635	total: 3.46s	remaining: 573ms
858:	learn: 0.3941913	total: 3.46s	remaining: 569ms
859:	learn: 0.3938834	total: 3.46s	remaining: 564ms
860:	learn: 0.3934388	total: 3.47s	remaining: 560ms
861:	learn: 0.3931506	total: 3.47s	remaining: 555ms
862:	learn: 0.3929385	total: 3.47s	remaining: 551ms
863:	learn: 0.3924647	total: 3.47s	remaining: 546ms
864:	learn: 0.3921215	total: 3.47s	remaining: 542ms
865:	learn: 0.3919831	total: 3.47s	remaining: 537ms
866:	learn: 0.3917143	total: 3.47s	remaining: 533ms
867:	learn: 0.3914015	total: 3.47s	remaining: 528ms
868:	learn: 0.3912759	total: 3.47s	remaining: 524ms
869:	learn: 0.3912660	total: 3.47s	remaining: 519ms
870:	learn: 0.3911801	total: 3.48s	remaining: 515ms
871:	learn: 0.3908668	total: 3.48s	remaining: 510ms
872:	learn: 0.3905618	total: 3.48s	remaining: 506ms
873:	learn: 0.3904840	total: 3.48s	remaining: 501ms
874:	learn: 0.3901271	total: 3.48s	remaining: 497ms
875:	learn: 0.3898932	total: 3.48s	remaining: 493ms
876:	learn: 0.3898756	total: 3.48s	remaining: 488ms
877:	learn: 0.3898579	total: 3.48s	remaining: 484ms
878:	learn: 0.3895947	total: 3.48s	remaining: 479ms
879:	learn: 0.3895143	total: 3.48s	remaining: 475ms
880:	learn: 0.3891604	total: 3.48s	remaining: 471ms
881:	learn: 0.3889210	total: 3.48s	remaining: 466ms
882:	learn: 0.3885842	total: 3.49s	remaining: 462ms
883:	learn: 0.3884881	total: 3.49s	remaining: 458ms
884:	learn: 0.3883898	total: 3.49s	remaining: 453ms
885:	learn: 0.3880547	total: 3.49s	remaining: 449ms
886:	learn: 0.3877016	total: 3.49s	remaining: 445ms
887:	learn: 0.3873718	total: 3.49s	remaining: 440ms
888:	learn: 0.3871575	total: 3.49s	remaining: 436ms
889:	learn: 0.3869107	total: 3.49s	remaining: 432ms
890:	learn: 0.3867117	total: 3.49s	remaining: 427ms
891:	learn: 0.3863501	total: 3.49s	remaining: 423ms
892:	learn: 0.3863085	total: 3.49s	remaining: 419ms
893:	learn: 0.3861340	total: 3.5s	remaining: 414ms
894:	learn: 0.3857751	total: 3.5s	remaining: 410ms
895:	learn: 0.3855087	total: 3.5s	remaining: 406ms
896:	learn: 0.3852027	total: 3.5s	remaining: 402ms
897:	learn: 0.3849918	total: 3.5s	remaining: 397ms
898:	learn: 0.3847259	total: 3.5s	remaining: 393ms
899:	learn: 0.3846838	total: 3.5s	remaining: 389ms
900:	learn: 0.3844182	total: 3.5s	remaining: 385ms
901:	learn: 0.3843628	total: 3.5s	remaining: 381ms
902:	learn: 0.3841346	total: 3.5s	remaining: 376ms
903:	learn: 0.3836597	total: 3.5s	remaining: 372ms
904:	learn: 0.3832317	total: 3.51s	remaining: 368ms
905:	learn: 0.3830497	total: 3.51s	remaining: 364ms
906:	learn: 0.3828969	total: 3.51s	remaining: 360ms
907:	learn: 0.3826313	total: 3.51s	remaining: 356ms
908:	learn: 0.3822036	total: 3.51s	remaining: 351ms
909:	learn: 0.3820192	total: 3.51s	remaining: 347ms
910:	learn: 0.3816567	total: 3.51s	remaining: 343ms
911:	learn: 0.3812102	total: 3.51s	remaining: 339ms
912:	learn: 0.3810945	total: 3.51s	remaining: 335ms
913:	learn: 0.3808702	total: 3.51s	remaining: 331ms
914:	learn: 0.3807187	total: 3.52s	remaining: 327ms
915:	learn: 0.3804485	total: 3.52s	remaining: 322ms
916:	learn: 0.3802377	total: 3.52s	remaining: 318ms
917:	learn: 0.3800245	total: 3.52s	remaining: 314ms
918:	learn: 0.3798408	total: 3.52s	remaining: 310ms
919:	learn: 0.3796811	total: 3.52s	remaining: 306ms
920:	learn: 0.3795281	total: 3.52s	remaining: 302ms
921:	learn: 0.3793421	total: 3.52s	remaining: 298ms
922:	learn: 0.3790304	total: 3.52s	remaining: 294ms
923:	learn: 0.3788460	total: 3.52s	remaining: 290ms
924:	learn: 0.3786925	total: 3.52s	remaining: 286ms
925:	learn: 0.3785577	total: 3.52s	remaining: 282ms
926:	learn: 0.3782526	total: 3.52s	remaining: 278ms
927:	learn: 0.3778582	total: 3.53s	remaining: 274ms
928:	learn: 0.3777924	total: 3.53s	remaining: 270ms
929:	learn: 0.3774347	total: 3.53s	remaining: 266ms
930:	learn: 0.3771597	total: 3.53s	remaining: 262ms
931:	learn: 0.3769098	total: 3.53s	remaining: 258ms
932:	learn: 0.3766663	total: 3.53s	remaining: 254ms
933:	learn: 0.3763730	total: 3.53s	remaining: 250ms
934:	learn: 0.3760467	total: 3.53s	remaining: 246ms
935:	learn: 0.3758021	total: 3.53s	remaining: 242ms
936:	learn: 0.3755592	total: 3.53s	remaining: 238ms
937:	learn: 0.3752168	total: 3.54s	remaining: 234ms
938:	learn: 0.3749841	total: 3.54s	remaining: 230ms
939:	learn: 0.3747918	total: 3.54s	remaining: 226ms
940:	learn: 0.3742311	total: 3.54s	remaining: 222ms
941:	learn: 0.3740204	total: 3.54s	remaining: 218ms
942:	learn: 0.3739633	total: 3.54s	remaining: 214ms
943:	learn: 0.3738071	total: 3.54s	remaining: 210ms
944:	learn: 0.3736811	total: 3.54s	remaining: 206ms
945:	learn: 0.3735288	total: 3.54s	remaining: 202ms
946:	learn: 0.3729451	total: 3.54s	remaining: 198ms
947:	learn: 0.3726811	total: 3.54s	remaining: 194ms
948:	learn: 0.3724009	total: 3.54s	remaining: 191ms
949:	learn: 0.3723473	total: 3.55s	remaining: 187ms
950:	learn: 0.3721981	total: 3.55s	remaining: 183ms
951:	learn: 0.3720880	total: 3.55s	remaining: 179ms
952:	learn: 0.3717661	total: 3.55s	remaining: 175ms
953:	learn: 0.3714623	total: 3.55s	remaining: 171ms
954:	learn: 0.3713678	total: 3.55s	remaining: 167ms
955:	learn: 0.3711545	total: 3.55s	remaining: 163ms
956:	learn: 0.3710523	total: 3.55s	remaining: 160ms
957:	learn: 0.3709052	total: 3.55s	remaining: 156ms
958:	learn: 0.3706837	total: 3.55s	remaining: 152ms
959:	learn: 0.3706360	total: 3.56s	remaining: 148ms
960:	learn: 0.3701820	total: 3.56s	remaining: 144ms
961:	learn: 0.3697476	total: 3.56s	remaining: 141ms
962:	learn: 0.3697240	total: 3.56s	remaining: 137ms
963:	learn: 0.3695370	total: 3.56s	remaining: 133ms
964:	learn: 0.3694622	total: 3.56s	remaining: 129ms
965:	learn: 0.3691361	total: 3.56s	remaining: 125ms
966:	learn: 0.3691278	total: 3.56s	remaining: 122ms
967:	learn: 0.3687988	total: 3.56s	remaining: 118ms
968:	learn: 0.3685147	total: 3.56s	remaining: 114ms
969:	learn: 0.3683037	total: 3.56s	remaining: 110ms
970:	learn: 0.3682930	total: 3.56s	remaining: 106ms
971:	learn: 0.3680178	total: 3.57s	remaining: 103ms
972:	learn: 0.3677760	total: 3.57s	remaining: 99ms
973:	learn: 0.3677694	total: 3.57s	remaining: 95.2ms
974:	learn: 0.3677544	total: 3.57s	remaining: 91.5ms
975:	learn: 0.3674684	total: 3.57s	remaining: 87.8ms
976:	learn: 0.3673247	total: 3.57s	remaining: 84.1ms
977:	learn: 0.3669150	total: 3.57s	remaining: 80.3ms
978:	learn: 0.3666510	total: 3.57s	remaining: 76.6ms
979:	learn: 0.3660816	total: 3.57s	remaining: 72.9ms
980:	learn: 0.3658024	total: 3.57s	remaining: 69.2ms
981:	learn: 0.3656007	total: 3.58s	remaining: 65.5ms
982:	learn: 0.3653716	total: 3.58s	remaining: 61.8ms
983:	learn: 0.3650935	total: 3.58s	remaining: 58.2ms
984:	learn: 0.3649617	total: 3.58s	remaining: 54.5ms
985:	learn: 0.3646536	total: 3.58s	remaining: 50.8ms
986:	learn: 0.3644866	total: 3.58s	remaining: 47.1ms
987:	learn: 0.3643401	total: 3.58s	remaining: 43.5ms
988:	learn: 0.3640844	total: 3.58s	remaining: 39.8ms
989:	learn: 0.3639551	total: 3.58s	remaining: 36.2ms
990:	learn: 0.3637711	total: 3.58s	remaining: 32.5ms
991:	learn: 0.3636161	total: 3.58s	remaining: 28.9ms
992:	learn: 0.3633803	total: 3.58s	remaining: 25.3ms
993:	learn: 0.3632255	total: 3.58s	remaining: 21.6ms
994:	learn: 0.3628812	total: 3.59s	remaining: 18ms
995:	learn: 0.3627984	total: 3.59s	remaining: 14.4ms
996:	learn: 0.3626012	total: 3.59s	remaining: 10.8ms
997:	learn: 0.3624386	total: 3.59s	remaining: 7.19ms
998:	learn: 0.3624278	total: 3.59s	remaining: 3.59ms
999:	learn: 0.3621817	total: 3.59s	remaining: 0us

error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

Prediction is good in CatBoost Regressor.

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

Not overfitted on Training set. So, this model is considered for final evaluation.

recorddata(modelname, pred_y_test, y_test, zero_to_one, one_to_two, two_to_three, greater_than_three, trn_time, pred_time)
model_name, r2_score_, mae,rmse,mse,error_0_to_1, error_1_to_2, error_2_to_3, error_greater_than_3, trn_time, pred_time

(['MultipleLinearRegression',
  'RidgeRegression',
  'RidgeRegression Tuned',
  'LassoRegression Tuned',
  'RandomForestRegressor',
  'RandomForestRegressor Tuned',
  'SupportVectorRegressor',
  'KNeighborsRegressor',
  'GradientBoosting Regressor',
  'CatBoostRegressor'],
 [0.5881944916179406,
  0.5882574872756139,
  0.5882500738453962,
  0.5195868929852978,
  0.6459987684820476,
  0.6115841548371949,
  0.6091219882096025,
  0.5950797047642148,
  0.6562976891201446,
  0.6844767215914438],
 [0.7570821537162007,
  0.7576445993512019,
  0.7570007300282396,
  0.839614296475421,
  0.6889759568590751,
  0.7237713897549489,
  0.7249561882292098,
  0.732286401098901,
  0.6931135058778565,
  0.6640694364813725],
 [1.022582311321646,
  1.0225040939257053,
  1.0225132989851697,
  1.1044844964051186,
  0.9481009607961802,
  0.9931175792144878,
  0.9962602910310709,
  1.013997706429134,
  0.9342076650826047,
  0.8950924689902702],
 [1.0456745834279195,
  1.0455146220948277,
  1.0455334466015351,
  1.2198860027992684,
  0.8988954318626401,
  0.9862825261448445,
  0.9925345674853142,
  1.028191348643544,
  0.872743961499092,
  0.8011905280430979],
 [133, 133, 133, 126, 139, 132, 138, 135, 136, 139],
 [38, 38, 38, 44, 33, 40, 28, 34, 36, 33],
 [8, 8, 8, 7, 9, 8, 13, 10, 9, 9],
 [3, 3, 3, 5, 1, 2, 3, 3, 1, 1],
 4.205406665802002,
 0.003617525100708008)

DecisionTreeRegressor

from sklearn.tree import DecisionTreeRegressor

modelname = 'DecisionTreeRegressor'
pred_y_test, pred_y_train, trn_time, pred_time = model_trainer(DecisionTreeRegressor(), x_train, y_train, x_test)
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred_y_test, y_test)
visualize_error(error, modelname)

From the above scatter plot we know that the model is quite bad than other models.

visulaize_performance_of_the_model(pred_y_test, y_test, modelname)

Prediction is not good in Decision Tree Regressor.

visualize_prediction_on_traindata(pred_y_train, y_train, modelname)

Decision Tree Regressor is highly overfitted on training set. So This model is not considered.

record = pd.DataFrame()

record['Model Name'], record['r2 Score'], record['Mean Absolute Error'], record['Mean Squared Error'], record['Root Mean Squared Error'], record['Error : 0 to 1'], record['Error : 1 to 2'], record['Error : 2 to 3'], record['Error : >3'], record['Training Time(Seconds)'], record['Prediction Time(Seconds)'] = model_name, r2_score_, mae, mse, rmse, error_0_to_1, error_1_to_2, error_2_to_3, error_greater_than_3, training_time, prediction_time

record

	Model Name	r2 Score	Mean Absolute Error	Mean Squared Error	Root Mean Squared Error	Error : 0 to 1	Error : 1 to 2	Error : 2 to 3	Error : >3	Training Time(Seconds)	Prediction Time(Seconds)
0	MultipleLinearRegression	0.588194	0.757082	1.045675	1.022582	133	38	8	3	0.108575	0.002001
1	RidgeRegression	0.588257	0.757645	1.045515	1.022504	133	38	8	3	0.006402	0.002459
2	RidgeRegression Tuned	0.588250	0.757001	1.045533	1.022513	133	38	8	3	0.002305	0.001282
3	LassoRegression Tuned	0.519587	0.839614	1.219886	1.104484	126	44	7	5	0.002421	0.000503
4	RandomForestRegressor	0.645999	0.688976	0.898895	0.948101	139	33	9	1	0.179502	0.008001
5	RandomForestRegressor Tuned	0.611584	0.723771	0.986283	0.993118	132	40	8	2	0.129106	0.006001
6	SupportVectorRegressor	0.609122	0.724956	0.992535	0.996260	138	28	13	3	0.023470	0.008002
7	KNeighborsRegressor	0.595080	0.732286	1.028191	1.013998	135	34	10	3	0.002404	0.002129
8	GradientBoosting Regressor	0.656298	0.693114	0.872744	0.934208	136	36	9	1	0.760219	0.013002
9	CatBoostRegressor	0.684477	0.664069	0.801191	0.895092	139	33	9	1	4.205407	0.003618

record.to_csv('EvaluationRecord.csv')

fig = go.Figure()
fig.add_trace(go.Scatter(y=record['r2 Score'],x=record['Model Name'],
                    mode='markers',
                    name='r2_score'))
fig.add_trace(go.Scatter(y=record['Mean Absolute Error'],x=record['Model Name'],
                    mode='markers',
                    name='Mean Absolute Error'))
fig.add_trace(go.Scatter(y=record['Mean Squared Error'],x=record['Model Name'],
                    mode='markers',
                    name='Mean Squared Error'))
fig.add_trace(go.Scatter(y=record['Root Mean Squared Error'],x=record['Model Name'],
                    mode='markers',
                    name='Root Mean Squared Error'))
fig.update_layout(
    title="Evaluation of the Model based on Scoring Metrics",
    xaxis_title="Model",
    yaxis_title="Score",
    legend_title_text="Scoring Metrics",
    font=dict(
        family="Courier New, monospace",
        size=13,
        color="RebeccaPurple"
    )
)
fig.show()

From the above plots. We have to choose the model which stays low in the graph.

From the above graph we pick stable models,

1) GradientBoosting Regressor,

2) CatBoost Regresssor,

3) RandomForest Regressor,

4) SupportVector Regressor &

5) RandomForest Regressor Tuned

stacked_barplot = pd.DataFrame()

model_name, error_range, count = [], [], []

for i in range(len(record)):
    model_name.append(record['Model Name'][i])
    model_name.append(record['Model Name'][i])
    model_name.append(record['Model Name'][i])
    model_name.append(record['Model Name'][i])
    error_range.append('Error : 0 to 1')
    error_range.append('Error : 1 to 2')
    error_range.append('Error : 2 to 3')
    error_range.append('Error : >3')
    count.append(record['Error : 0 to 1'][i])
    count.append(record['Error : 1 to 2'][i])
    count.append(record['Error : 2 to 3'][i])
    count.append(record['Error : >3'][i])

model_name, error_range, count

(['MultipleLinearRegression',
  'MultipleLinearRegression',
  'MultipleLinearRegression',
  'MultipleLinearRegression',
  'RidgeRegression',
  'RidgeRegression',
  'RidgeRegression',
  'RidgeRegression',
  'RidgeRegression Tuned',
  'RidgeRegression Tuned',
  'RidgeRegression Tuned',
  'RidgeRegression Tuned',
  'LassoRegression Tuned',
  'LassoRegression Tuned',
  'LassoRegression Tuned',
  'LassoRegression Tuned',
  'RandomForestRegressor',
  'RandomForestRegressor',
  'RandomForestRegressor',
  'RandomForestRegressor',
  'RandomForestRegressor Tuned',
  'RandomForestRegressor Tuned',
  'RandomForestRegressor Tuned',
  'RandomForestRegressor Tuned',
  'SupportVectorRegressor',
  'SupportVectorRegressor',
  'SupportVectorRegressor',
  'SupportVectorRegressor',
  'KNeighborsRegressor',
  'KNeighborsRegressor',
  'KNeighborsRegressor',
  'KNeighborsRegressor',
  'GradientBoosting Regressor',
  'GradientBoosting Regressor',
  'GradientBoosting Regressor',
  'GradientBoosting Regressor',
  'CatBoostRegressor',
  'CatBoostRegressor',
  'CatBoostRegressor',
  'CatBoostRegressor'],
 ['Error : 0 to 1',
  'Error : 1 to 2',
  'Error : 2 to 3',
  'Error : >3',
  'Error : 0 to 1',
  'Error : 1 to 2',
  'Error : 2 to 3',
  'Error : >3',
  'Error : 0 to 1',
  'Error : 1 to 2',
  'Error : 2 to 3',
  'Error : >3',
  'Error : 0 to 1',
  'Error : 1 to 2',
  'Error : 2 to 3',
  'Error : >3',
  'Error : 0 to 1',
  'Error : 1 to 2',
  'Error : 2 to 3',
  'Error : >3',
  'Error : 0 to 1',
  'Error : 1 to 2',
  'Error : 2 to 3',
  'Error : >3',
  'Error : 0 to 1',
  'Error : 1 to 2',
  'Error : 2 to 3',
  'Error : >3',
  'Error : 0 to 1',
  'Error : 1 to 2',
  'Error : 2 to 3',
  'Error : >3',
  'Error : 0 to 1',
  'Error : 1 to 2',
  'Error : 2 to 3',
  'Error : >3',
  'Error : 0 to 1',
  'Error : 1 to 2',
  'Error : 2 to 3',
  'Error : >3'],
 [133,
  38,
  8,
  3,
  133,
  38,
  8,
  3,
  133,
  38,
  8,
  3,
  126,
  44,
  7,
  5,
  139,
  33,
  9,
  1,
  132,
  40,
  8,
  2,
  138,
  28,
  13,
  3,
  135,
  34,
  10,
  3,
  136,
  36,
  9,
  1,
  139,
  33,
  9,
  1])

stacked_barplot['model_name'], stacked_barplot['error_range'], stacked_barplot['count'] = model_name, error_range, count

stacked_barplot

	model_name	error_range	count
0	MultipleLinearRegression	Error : 0 to 1	133
1	MultipleLinearRegression	Error : 1 to 2	38
2	MultipleLinearRegression	Error : 2 to 3	8
3	MultipleLinearRegression	Error : >3	3
4	RidgeRegression	Error : 0 to 1	133
5	RidgeRegression	Error : 1 to 2	38
6	RidgeRegression	Error : 2 to 3	8
7	RidgeRegression	Error : >3	3
8	RidgeRegression Tuned	Error : 0 to 1	133
9	RidgeRegression Tuned	Error : 1 to 2	38
10	RidgeRegression Tuned	Error : 2 to 3	8
11	RidgeRegression Tuned	Error : >3	3
12	LassoRegression Tuned	Error : 0 to 1	126
13	LassoRegression Tuned	Error : 1 to 2	44
14	LassoRegression Tuned	Error : 2 to 3	7
15	LassoRegression Tuned	Error : >3	5
16	RandomForestRegressor	Error : 0 to 1	139
17	RandomForestRegressor	Error : 1 to 2	33
18	RandomForestRegressor	Error : 2 to 3	9
19	RandomForestRegressor	Error : >3	1
20	RandomForestRegressor Tuned	Error : 0 to 1	132
21	RandomForestRegressor Tuned	Error : 1 to 2	40
22	RandomForestRegressor Tuned	Error : 2 to 3	8
23	RandomForestRegressor Tuned	Error : >3	2
24	SupportVectorRegressor	Error : 0 to 1	138
25	SupportVectorRegressor	Error : 1 to 2	28
26	SupportVectorRegressor	Error : 2 to 3	13
27	SupportVectorRegressor	Error : >3	3
28	KNeighborsRegressor	Error : 0 to 1	135
29	KNeighborsRegressor	Error : 1 to 2	34
30	KNeighborsRegressor	Error : 2 to 3	10
31	KNeighborsRegressor	Error : >3	3
32	GradientBoosting Regressor	Error : 0 to 1	136
33	GradientBoosting Regressor	Error : 1 to 2	36
34	GradientBoosting Regressor	Error : 2 to 3	9
35	GradientBoosting Regressor	Error : >3	1
36	CatBoostRegressor	Error : 0 to 1	139
37	CatBoostRegressor	Error : 1 to 2	33
38	CatBoostRegressor	Error : 2 to 3	9
39	CatBoostRegressor	Error : >3	1

fig = plx.bar(stacked_barplot, x="model_name", y="count", color="error_range", height=1000)
fig.update_layout(
    title="Performance of the all models on Test Data",
    xaxis_title="Model",
    yaxis_title="Count of Test data",
    legend_title_text="Error Range",
    font=dict(
        family="Courier New, monospace",
        size=13,
        color="RebeccaPurple"
    )
)
fig.show()

We can save the best model which is good i.e., CatBoost Regressor

Traditional way ends here......

Diving Deep into the Dataset.....

First, we're not satisfied with the r2_score numbers on training and testing in all Algorithms. There's a huge difference. We cant' pick any one of them and end here.....

From all visualization we notice that the training is good but prediction accuracy is far away from the training accuracy. So, we confirm that there is a problem in Dataset.

To be honest, we're picking one best model out of the 10 models based on only one set of train and test split. In my point of view this is not the right way of picking best model. Every algorithm learns in a different way. This case is diiferent so we have to handle it in a different way.

Here, we're going to run some of the algorithms for 'n' times with 'n' different train & test split. Then, calculating r2 score of both training and testing set for each split and stored it in a list for all considered algorithm.

Then visualizing it.

score_gbr,score_cbr,score_rfr,score_svr,score_mlr = [],[],[],[],[]
score_gbr_trn, score_cbr_trn, score_rfr_trn, score_svr_trn, score_mlr_trn = [],[],[],[],[]
for i in tqdm(range(3000)):
    x_train, x_test, y_train, y_test = train_test_split(data.drop(['LC50'], axis = 1), data['LC50'], test_size= 0.2)
    
    gbr = GradientBoostingRegressor(verbose=0).fit(x_train, y_train)
    cbr = CatBoostRegressor(verbose=0).fit(x_train, y_train)
    rfr = RandomForestRegressor(verbose=0).fit(x_train, y_train)
    svr = SVR().fit(x_train, y_train)
    mlr = LinearRegression().fit(x_train, y_train)
    
    pred_gbr = gbr.predict(x_test)
    score_gbr.append(r2_score(y_test, pred_gbr))
    pred_gbr_trn = gbr.predict(x_train)
    score_gbr_trn.append(r2_score(y_train, pred_gbr_trn))
    
    pred_cbr = cbr.predict(x_test)
    score_cbr.append(r2_score(y_test, pred_cbr))
    pred_cbr_trn = cbr.predict(x_train)
    score_cbr_trn.append(r2_score(y_train, pred_cbr_trn))
    
    pred_rfr = rfr.predict(x_test)
    score_rfr.append(r2_score(y_test, pred_rfr))
    pred_rfr_trn = rfr.predict(x_train)
    score_rfr_trn.append(r2_score(y_train, pred_rfr_trn))
    
    pred_svr = svr.predict(x_test)
    score_svr.append(r2_score(y_test, pred_svr))
    pred_svr_trn = svr.predict(x_train)
    score_svr_trn.append(r2_score(y_train, pred_svr_trn))
    
    pred_mlr = mlr.predict(x_test)
    score_mlr.append(r2_score(y_test, pred_mlr))
    pred_mlr_trn = mlr.predict(x_train)
    score_mlr_trn.append(r2_score(y_train, pred_mlr_trn))

100%|██████████| 3000/3000 [1:03:09<00:00,  1.26s/it]

Checking Goodness of Algorithm on Both Training &Testing Data

1)Gradient Boosting Regressor

from plotly.subplots import make_subplots
import plotly.graph_objects as go

fig = make_subplots(rows = 2, cols = 1)

fig.append_trace(go.Scatter(y = score_gbr, name = 'Test Score'), row=1, col=1)
fig.append_trace(go.Scatter(y = score_gbr_trn, name = 'Train Score'), row=2, col=1)

fig.update_layout(title = 'Train vs Test Score on GradientBoosting Regressor')
fig.show()

In GradienBoosting Regressor, most of the Train Score is inbetween 0.81 and 0.84. But, the test score is around 0.60. There is a huge gap between Train & Test Score.

Let's check with all algorithms and decide.

2) CatBoost Regressor

fig = make_subplots(rows = 2, cols = 1)

fig.append_trace(go.Scatter(y = score_cbr, name = 'Test Score'), row=1, col=1)
fig.append_trace(go.Scatter(y = score_cbr_trn, name = 'Train Score'), row=2, col=1)

fig.update_layout(title = 'Train vs Test Score on CatBoost Regressor')
fig.show()

In CatBoost Regressor, most of the Train Score is inbetween 0.93 and 0.95. But, the test score is around 0.65. There is a huge gap between Train & Test Score.

3) RandomForest Regressor

fig = make_subplots(rows = 2, cols = 1)

fig.append_trace(go.Scatter(y = score_rfr, name = 'Test Score'), row=1, col=1)
fig.append_trace(go.Scatter(y = score_rfr_trn, name = 'Train Score'), row=2, col=1)

fig.update_layout(title = 'Train vs Test Score on RandomForest Regressor')
fig.show()

In RandomForest Regressor, most of the Train Score is inbetween 0.93 and 0.94. But, the test score is around 0.65. There is a huge gap between Train & Test Score.

4) SupportVector Regressor

fig = make_subplots(rows = 2, cols = 1)

fig.append_trace(go.Scatter(y = score_svr, name = 'Test Score'), row=1, col=1)
fig.append_trace(go.Scatter(y = score_svr_trn, name = 'Train Score'), row=2, col=1)

fig.update_layout(title = 'Train vs Test Score on SupportVector Regressor')
fig.show()

In SupportVector Regressor, most of the Train Score is around 0.65. And, the test score is around 0.60.

5) MultipleLinear Regression

fig = make_subplots(rows = 2, cols = 1)

fig.append_trace(go.Scatter(y = score_mlr, name = 'Test Score'), row=1, col=1)
fig.append_trace(go.Scatter(y = score_mlr_trn, name = 'Train Score'), row=2, col=1)

fig.update_layout(title = 'Train vs Test Score on MultipleLinear Regression')
fig.show()

In MultipleLinear Regression, most of the Train Score is around 0.57. Huge Margin between train and test score.

We got 'n' number of train and test score of each model and made a comparision.

Let consider RandomForest Regressor and CatBoost Regressor. There's a lot of gap between train and test score.

Train Score for 2 models mentioned above are good(more than 0.9). But, huge drop while comes to Test score i.e., avearge of 0.6.

Sometimes, the test score falls to 0.4 which is too bad when compared to Train score.

Why this is happening? is the first question for us....

We've to find the ROOT CAUSE of this problem.

We have to check the dataset deeply. So that we can find, In which record the error is high?.

Here also we're running the process for 'n' number of times. Then only we know where the problem arise.

Here, we're checking where the problem arise. So we consider the record as failure if the testing record having error more than 1(Here, the reason for considering failure margin as 1 is that the error of train data not exceeded 1 when train set was fed into the model). While running 'n' number of times, we can get the problamatic records.

pd.set_option("display.max_rows", None)

data_check = data.copy()
data_check['Count of Failure'] = np.zeros(len(data_check))
data_check

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50	Count of Failure
0	3.260	0.829	1.676	0	1	1.453	3.770	0.0
1	2.189	0.580	0.863	0	0	1.348	3.115	0.0
2	2.125	0.638	0.831	0	0	1.348	3.531	0.0
3	3.027	0.331	1.472	1	0	1.807	3.510	0.0
4	2.094	0.827	0.860	0	0	1.886	5.390	0.0
...	...	...	...	...	...	...	...	...
903	2.801	0.728	2.226	0	2	0.736	3.109	0.0
904	3.652	0.872	0.867	2	3	3.983	4.040	0.0
905	3.763	0.916	0.878	0	6	2.918	4.818	0.0
906	2.831	1.393	1.077	0	1	0.906	5.317	0.0
907	4.057	1.032	1.183	1	3	4.754	8.201	0.0

907 rows × 8 columns

data_check = data.copy()
data_check['Count of Failure'] = np.zeros(len(data_check))
for i in tqdm(range(3000)):
    x_train, x_test, y_train, y_test = train_test_split(data.drop(['LC50'], axis = 1), data['LC50'], test_size= 0.2)
    cbr = CatBoostRegressor(verbose=0).fit(x_train, y_train)
    for i in range(len(x_test)):
        pred = cbr.predict(x_test.iloc[i])
        error = abs(pred - y_test.iloc[i])
        if error >=1:
            find = data_check.loc[((data_check['CIC0'] == x_test.iloc[i][0]) & (data_check['SM1_Dz(Z)'] == x_test.iloc[i][1]) & (data_check['GATS1i'] == x_test.iloc[i][2]) & (data_check['NdsCH'] == x_test.iloc[i][3]) & (data_check['NdssC'] == x_test.iloc[i][4]) & (data_check['MLOGP'] == x_test.iloc[i][5]) )]
            count = find['Count of Failure']
            count += 1                      
            data_check.loc[( (data_check['CIC0'] == x_test.iloc[i][0]) &
                            (data_check['SM1_Dz(Z)'] == x_test.iloc[i][1]) &
                            (data_check['GATS1i'] == x_test.iloc[i][2]) &
                            (data_check['NdsCH'] == x_test.iloc[i][3]) &
                            (data_check['NdssC'] == x_test.iloc[i][4]) &
                            (data_check['MLOGP'] == x_test.iloc[i][5]) ), 'Count of Failure'] = count
        else:
            pass

100%|██████████| 3000/3000 [55:00<00:00,  1.10s/it]

data_check.sort_values(by='Count of Failure', ascending=False, inplace=True)
data_check

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50	Count of Failure
97	2.359	0.405	0.814	0	0	0.893	3.314	1266.0
219	2.359	0.405	0.814	0	0	0.893	6.400	1266.0
196	2.359	0.405	0.814	0	0	0.893	4.287	1266.0
175	2.544	0.223	1.245	0	0	1.064	1.408	1071.0
351	2.544	0.223	1.245	0	0	1.064	3.380	1071.0
...	...	...	...	...	...	...	...	...
397	3.128	0.713	0.797	0	1	4.017	5.039	0.0
398	2.417	1.028	1.162	0	1	3.190	4.169	0.0
399	3.055	1.273	1.132	0	0	2.931	5.393	0.0
404	2.647	1.286	1.278	0	0	1.602	4.508	0.0
453	3.316	0.223	1.571	1	0	1.795	3.854	0.0

907 rows × 8 columns

By seeing the record's head, we can see that the duplication in independent variable which has the same count value of Failure. The independent variables are same but target is different. We have to remove those duplicate records as well as the original record. They are not real. We really don't know which 'LC50' value is real for those duplicates.

Let's start from beginning..

Importing Dataset

df = pd.read_csv('C:\\Users\\harip\\INEURON_PROJECTS\\Prediction of LC50\\LC50_Project\\data\\dataset(csv)\\qsar_fish_toxicity.csv', header = None, delimiter = ';', names = column_names)
df

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50
0	3.260	0.829	1.676	0	1	1.453	3.770
1	2.189	0.580	0.863	0	0	1.348	3.115
2	2.125	0.638	0.831	0	0	1.348	3.531
3	3.027	0.331	1.472	1	0	1.807	3.510
4	2.094	0.827	0.860	0	0	1.886	5.390
...	...	...	...	...	...	...	...
903	2.801	0.728	2.226	0	2	0.736	3.109
904	3.652	0.872	0.867	2	3	3.983	4.040
905	3.763	0.916	0.878	0	6	2.918	4.818
906	2.831	1.393	1.077	0	1	0.906	5.317
907	4.057	1.032	1.183	1	3	4.754	8.201

908 rows × 7 columns

Removing Duplicates

df.drop_duplicates(inplace=True)
df.reset_index(inplace=True, drop=True)
df

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50
0	3.260	0.829	1.676	0	1	1.453	3.770
1	2.189	0.580	0.863	0	0	1.348	3.115
2	2.125	0.638	0.831	0	0	1.348	3.531
3	3.027	0.331	1.472	1	0	1.807	3.510
4	2.094	0.827	0.860	0	0	1.886	5.390
...	...	...	...	...	...	...	...
902	2.801	0.728	2.226	0	2	0.736	3.109
903	3.652	0.872	0.867	2	3	3.983	4.040
904	3.763	0.916	0.878	0	6	2.918	4.818
905	2.831	1.393	1.077	0	1	0.906	5.317
906	4.057	1.032	1.183	1	3	4.754	8.201

907 rows × 7 columns

Removing Duplicates of Independent variables

index = []
for i in tqdm(range(0,len(data))):
    col1, col2, col3, col4, col5, col6 = df['CIC0'][i], df['SM1_Dz(Z)'][i], df['GATS1i'][i], df['NdsCH'][i], df['NdssC'][i], df['MLOGP'][i]
    for j in range(0,len(data)):
        if (j != i) & (df['CIC0'][j] == col1) & (df['SM1_Dz(Z)'][j] == col2) & (df['GATS1i'][j] == col3) & (df['NdsCH'][j] == col4) & (df['NdssC'][j] == col5) & (df['MLOGP'][j] == col6):
            index.append(j)
            index.append(i)
        else:
            continue
df = df.drop(list(set(index)))
df = df.reset_index(drop=True)

100%|██████████| 907/907 [00:18<00:00, 48.69it/s]

df

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50
0	3.260	0.829	1.676	0	1	1.453	3.770
1	2.189	0.580	0.863	0	0	1.348	3.115
2	3.027	0.331	1.472	1	0	1.807	3.510
3	3.222	0.331	2.177	0	0	0.706	1.819
4	3.000	0.000	0.938	1	0	2.851	3.513
...	...	...	...	...	...	...	...
686	2.801	0.728	2.226	0	2	0.736	3.109
687	3.652	0.872	0.867	2	3	3.983	4.040
688	3.763	0.916	0.878	0	6	2.918	4.818
689	2.831	1.393	1.077	0	1	0.906	5.317
690	4.057	1.032	1.183	1	3	4.754	8.201

691 rows × 7 columns

Here, we removed all records related to duplicates a total of 216 out of 907 records.

Now, we can try one of the Algorithm to check the performance

x_train, x_test, y_train, y_test = train_test_split(df.drop(['LC50'], axis = 1), df['LC50'], test_size= 0.2)
cbr = CatBoostRegressor().fit(x_train, y_train)
pred = cbr.predict(x_test)
pred_cbr_trn = cbr.predict(x_train)
modelname = 'CatBoostRegressor Checking'
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred, y_test)
visualize_error(error, modelname)

Learning rate set to 0.037274
0:	learn: 1.4720476	total: 1.05ms	remaining: 1.05s
1:	learn: 1.4467590	total: 1.9ms	remaining: 946ms
2:	learn: 1.4252102	total: 2.66ms	remaining: 884ms
3:	learn: 1.4035975	total: 3.4ms	remaining: 846ms
4:	learn: 1.3814955	total: 4.13ms	remaining: 822ms
5:	learn: 1.3614009	total: 4.88ms	remaining: 809ms
6:	learn: 1.3400333	total: 5.62ms	remaining: 797ms
7:	learn: 1.3201236	total: 6.37ms	remaining: 790ms
8:	learn: 1.3023377	total: 6.91ms	remaining: 761ms
9:	learn: 1.2839488	total: 7.67ms	remaining: 759ms
10:	learn: 1.2672481	total: 8.4ms	remaining: 755ms
11:	learn: 1.2524079	total: 9.18ms	remaining: 756ms
12:	learn: 1.2383070	total: 10ms	remaining: 762ms
13:	learn: 1.2241592	total: 10.8ms	remaining: 760ms
14:	learn: 1.2091198	total: 11.6ms	remaining: 759ms
15:	learn: 1.1945168	total: 12.3ms	remaining: 759ms
16:	learn: 1.1796376	total: 13.1ms	remaining: 758ms
17:	learn: 1.1668922	total: 13.9ms	remaining: 756ms
18:	learn: 1.1548163	total: 14.6ms	remaining: 753ms
19:	learn: 1.1434681	total: 15.3ms	remaining: 752ms
20:	learn: 1.1323627	total: 16.1ms	remaining: 750ms
21:	learn: 1.1217924	total: 16.8ms	remaining: 748ms
22:	learn: 1.1119316	total: 17.7ms	remaining: 753ms
23:	learn: 1.1016965	total: 18.5ms	remaining: 754ms
24:	learn: 1.0917330	total: 19.4ms	remaining: 756ms
25:	learn: 1.0825266	total: 20.2ms	remaining: 756ms
26:	learn: 1.0745128	total: 21ms	remaining: 756ms
27:	learn: 1.0658925	total: 21.7ms	remaining: 755ms
28:	learn: 1.0574134	total: 22.5ms	remaining: 754ms
29:	learn: 1.0493361	total: 23.3ms	remaining: 754ms
30:	learn: 1.0412830	total: 24.1ms	remaining: 755ms
31:	learn: 1.0345641	total: 24.9ms	remaining: 754ms
32:	learn: 1.0283647	total: 25.7ms	remaining: 752ms
33:	learn: 1.0208700	total: 26.5ms	remaining: 752ms
34:	learn: 1.0142679	total: 27.3ms	remaining: 753ms
35:	learn: 1.0102777	total: 27.8ms	remaining: 745ms
36:	learn: 1.0041967	total: 28.6ms	remaining: 745ms
37:	learn: 0.9983584	total: 29.4ms	remaining: 745ms
38:	learn: 0.9919160	total: 30.3ms	remaining: 747ms
39:	learn: 0.9861160	total: 31.1ms	remaining: 746ms
40:	learn: 0.9801863	total: 31.9ms	remaining: 746ms
41:	learn: 0.9754462	total: 32.6ms	remaining: 745ms
42:	learn: 0.9705738	total: 33.5ms	remaining: 745ms
43:	learn: 0.9649056	total: 34.3ms	remaining: 745ms
44:	learn: 0.9609176	total: 35.1ms	remaining: 745ms
45:	learn: 0.9564052	total: 35.8ms	remaining: 743ms
46:	learn: 0.9521809	total: 36.7ms	remaining: 744ms
47:	learn: 0.9478252	total: 37.5ms	remaining: 745ms
48:	learn: 0.9440688	total: 38.3ms	remaining: 743ms
49:	learn: 0.9394232	total: 39.1ms	remaining: 742ms
50:	learn: 0.9348663	total: 39.8ms	remaining: 741ms
51:	learn: 0.9303876	total: 40.6ms	remaining: 741ms
52:	learn: 0.9263828	total: 41.4ms	remaining: 740ms
53:	learn: 0.9214747	total: 42.2ms	remaining: 739ms
54:	learn: 0.9178980	total: 43ms	remaining: 739ms
55:	learn: 0.9136295	total: 43.8ms	remaining: 738ms
56:	learn: 0.9104948	total: 44.6ms	remaining: 738ms
57:	learn: 0.9068519	total: 45.4ms	remaining: 738ms
58:	learn: 0.9029138	total: 46.3ms	remaining: 738ms
59:	learn: 0.8992578	total: 47.1ms	remaining: 738ms
60:	learn: 0.8958032	total: 47.9ms	remaining: 738ms
61:	learn: 0.8923628	total: 48.8ms	remaining: 738ms
62:	learn: 0.8883986	total: 49.6ms	remaining: 738ms
63:	learn: 0.8863561	total: 50.4ms	remaining: 738ms
64:	learn: 0.8830771	total: 51.2ms	remaining: 737ms
65:	learn: 0.8808577	total: 52.1ms	remaining: 737ms
66:	learn: 0.8783017	total: 52.9ms	remaining: 736ms
67:	learn: 0.8752602	total: 53.6ms	remaining: 735ms
68:	learn: 0.8726959	total: 54.4ms	remaining: 734ms
69:	learn: 0.8703346	total: 55.2ms	remaining: 734ms
70:	learn: 0.8677730	total: 56ms	remaining: 733ms
71:	learn: 0.8652139	total: 56.9ms	remaining: 733ms
72:	learn: 0.8629594	total: 57.7ms	remaining: 733ms
73:	learn: 0.8599990	total: 58.5ms	remaining: 732ms
74:	learn: 0.8573533	total: 59.4ms	remaining: 732ms
75:	learn: 0.8551064	total: 60.1ms	remaining: 731ms
76:	learn: 0.8530011	total: 61ms	remaining: 732ms
77:	learn: 0.8506375	total: 61.9ms	remaining: 732ms
78:	learn: 0.8482384	total: 62.7ms	remaining: 731ms
79:	learn: 0.8444458	total: 63.5ms	remaining: 731ms
80:	learn: 0.8429558	total: 64.3ms	remaining: 730ms
81:	learn: 0.8398881	total: 65.1ms	remaining: 728ms
82:	learn: 0.8370909	total: 65.8ms	remaining: 727ms
83:	learn: 0.8351714	total: 66.6ms	remaining: 727ms
84:	learn: 0.8317379	total: 67.4ms	remaining: 726ms
85:	learn: 0.8300322	total: 68.2ms	remaining: 725ms
86:	learn: 0.8281276	total: 69ms	remaining: 724ms
87:	learn: 0.8268751	total: 69.7ms	remaining: 723ms
88:	learn: 0.8254791	total: 70.5ms	remaining: 722ms
89:	learn: 0.8240697	total: 71.3ms	remaining: 720ms
90:	learn: 0.8233619	total: 72ms	remaining: 719ms
91:	learn: 0.8216848	total: 72.8ms	remaining: 719ms
92:	learn: 0.8193057	total: 73.6ms	remaining: 718ms
93:	learn: 0.8172480	total: 74.5ms	remaining: 718ms
94:	learn: 0.8153388	total: 75.4ms	remaining: 719ms
95:	learn: 0.8139059	total: 76.2ms	remaining: 718ms
96:	learn: 0.8121766	total: 77.1ms	remaining: 717ms
97:	learn: 0.8107525	total: 77.9ms	remaining: 717ms
98:	learn: 0.8093043	total: 78.6ms	remaining: 716ms
99:	learn: 0.8078338	total: 79.4ms	remaining: 715ms
100:	learn: 0.8061498	total: 80.2ms	remaining: 714ms
101:	learn: 0.8045511	total: 81ms	remaining: 713ms
102:	learn: 0.8037476	total: 81.7ms	remaining: 712ms
103:	learn: 0.8016140	total: 82.6ms	remaining: 711ms
104:	learn: 0.7995881	total: 83.5ms	remaining: 712ms
105:	learn: 0.7984627	total: 84.3ms	remaining: 711ms
106:	learn: 0.7968478	total: 85.1ms	remaining: 711ms
107:	learn: 0.7946010	total: 86ms	remaining: 710ms
108:	learn: 0.7937773	total: 86.8ms	remaining: 710ms
109:	learn: 0.7923437	total: 87.8ms	remaining: 711ms
110:	learn: 0.7906316	total: 88.7ms	remaining: 710ms
111:	learn: 0.7892278	total: 89.5ms	remaining: 710ms
112:	learn: 0.7882918	total: 90.4ms	remaining: 709ms
113:	learn: 0.7867117	total: 91.2ms	remaining: 709ms
114:	learn: 0.7857475	total: 92ms	remaining: 708ms
115:	learn: 0.7841698	total: 92.8ms	remaining: 707ms
116:	learn: 0.7824839	total: 93.7ms	remaining: 707ms
117:	learn: 0.7823829	total: 94ms	remaining: 702ms
118:	learn: 0.7813070	total: 94.8ms	remaining: 702ms
119:	learn: 0.7804675	total: 95.6ms	remaining: 701ms
120:	learn: 0.7791495	total: 96.4ms	remaining: 701ms
121:	learn: 0.7780101	total: 97.2ms	remaining: 700ms
122:	learn: 0.7773633	total: 98ms	remaining: 699ms
123:	learn: 0.7762684	total: 98.7ms	remaining: 698ms
124:	learn: 0.7750071	total: 99.6ms	remaining: 697ms
125:	learn: 0.7740166	total: 100ms	remaining: 697ms
126:	learn: 0.7736986	total: 101ms	remaining: 696ms
127:	learn: 0.7728988	total: 102ms	remaining: 695ms
128:	learn: 0.7723891	total: 103ms	remaining: 694ms
129:	learn: 0.7704541	total: 104ms	remaining: 693ms
130:	learn: 0.7688116	total: 104ms	remaining: 692ms
131:	learn: 0.7683515	total: 105ms	remaining: 691ms
132:	learn: 0.7669368	total: 106ms	remaining: 690ms
133:	learn: 0.7660927	total: 107ms	remaining: 689ms
134:	learn: 0.7649426	total: 107ms	remaining: 688ms
135:	learn: 0.7644772	total: 108ms	remaining: 687ms
136:	learn: 0.7634971	total: 109ms	remaining: 686ms
137:	learn: 0.7609113	total: 110ms	remaining: 685ms
138:	learn: 0.7598151	total: 110ms	remaining: 683ms
139:	learn: 0.7590354	total: 111ms	remaining: 681ms
140:	learn: 0.7580149	total: 112ms	remaining: 680ms
141:	learn: 0.7564872	total: 112ms	remaining: 679ms
142:	learn: 0.7557443	total: 113ms	remaining: 678ms
143:	learn: 0.7544180	total: 114ms	remaining: 676ms
144:	learn: 0.7535104	total: 114ms	remaining: 675ms
145:	learn: 0.7525846	total: 115ms	remaining: 675ms
146:	learn: 0.7520643	total: 116ms	remaining: 674ms
147:	learn: 0.7512078	total: 117ms	remaining: 673ms
148:	learn: 0.7502337	total: 118ms	remaining: 672ms
149:	learn: 0.7492231	total: 118ms	remaining: 671ms
150:	learn: 0.7486320	total: 119ms	remaining: 668ms
151:	learn: 0.7480431	total: 120ms	remaining: 667ms
152:	learn: 0.7479463	total: 120ms	remaining: 664ms
153:	learn: 0.7474241	total: 121ms	remaining: 663ms
154:	learn: 0.7470096	total: 121ms	remaining: 661ms
155:	learn: 0.7463405	total: 122ms	remaining: 660ms
156:	learn: 0.7444308	total: 123ms	remaining: 659ms
157:	learn: 0.7434153	total: 124ms	remaining: 658ms
158:	learn: 0.7427556	total: 124ms	remaining: 657ms
159:	learn: 0.7421641	total: 125ms	remaining: 656ms
160:	learn: 0.7408703	total: 126ms	remaining: 655ms
161:	learn: 0.7402518	total: 126ms	remaining: 654ms
162:	learn: 0.7398003	total: 127ms	remaining: 653ms
163:	learn: 0.7395245	total: 128ms	remaining: 652ms
164:	learn: 0.7386217	total: 129ms	remaining: 651ms
165:	learn: 0.7378744	total: 129ms	remaining: 650ms
166:	learn: 0.7370483	total: 130ms	remaining: 649ms
167:	learn: 0.7363265	total: 131ms	remaining: 648ms
168:	learn: 0.7355678	total: 132ms	remaining: 647ms
169:	learn: 0.7345352	total: 132ms	remaining: 646ms
170:	learn: 0.7333321	total: 133ms	remaining: 645ms
171:	learn: 0.7325637	total: 134ms	remaining: 644ms
172:	learn: 0.7320605	total: 134ms	remaining: 643ms
173:	learn: 0.7310167	total: 135ms	remaining: 642ms
174:	learn: 0.7302197	total: 136ms	remaining: 641ms
175:	learn: 0.7296345	total: 137ms	remaining: 640ms
176:	learn: 0.7288051	total: 137ms	remaining: 639ms
177:	learn: 0.7276860	total: 138ms	remaining: 638ms
178:	learn: 0.7269849	total: 139ms	remaining: 637ms
179:	learn: 0.7265813	total: 140ms	remaining: 636ms
180:	learn: 0.7249236	total: 140ms	remaining: 635ms
181:	learn: 0.7244637	total: 141ms	remaining: 633ms
182:	learn: 0.7241493	total: 142ms	remaining: 633ms
183:	learn: 0.7236957	total: 142ms	remaining: 632ms
184:	learn: 0.7228763	total: 143ms	remaining: 631ms
185:	learn: 0.7216117	total: 144ms	remaining: 630ms
186:	learn: 0.7202442	total: 145ms	remaining: 629ms
187:	learn: 0.7193244	total: 145ms	remaining: 628ms
188:	learn: 0.7189949	total: 146ms	remaining: 627ms
189:	learn: 0.7182657	total: 147ms	remaining: 626ms
190:	learn: 0.7175645	total: 148ms	remaining: 625ms
191:	learn: 0.7167055	total: 148ms	remaining: 625ms
192:	learn: 0.7147846	total: 149ms	remaining: 624ms
193:	learn: 0.7125122	total: 150ms	remaining: 623ms
194:	learn: 0.7119968	total: 151ms	remaining: 622ms
195:	learn: 0.7111730	total: 151ms	remaining: 621ms
196:	learn: 0.7106438	total: 152ms	remaining: 620ms
197:	learn: 0.7099948	total: 153ms	remaining: 619ms
198:	learn: 0.7094399	total: 154ms	remaining: 618ms
199:	learn: 0.7080068	total: 154ms	remaining: 617ms
200:	learn: 0.7077692	total: 155ms	remaining: 617ms
201:	learn: 0.7073947	total: 156ms	remaining: 616ms
202:	learn: 0.7070849	total: 157ms	remaining: 615ms
203:	learn: 0.7061662	total: 157ms	remaining: 614ms
204:	learn: 0.7055199	total: 158ms	remaining: 613ms
205:	learn: 0.7051495	total: 159ms	remaining: 612ms
206:	learn: 0.7047084	total: 159ms	remaining: 611ms
207:	learn: 0.7041134	total: 160ms	remaining: 610ms
208:	learn: 0.7039266	total: 161ms	remaining: 608ms
209:	learn: 0.7035198	total: 161ms	remaining: 607ms
210:	learn: 0.7031293	total: 162ms	remaining: 606ms
211:	learn: 0.7018907	total: 163ms	remaining: 605ms
212:	learn: 0.7011583	total: 164ms	remaining: 605ms
213:	learn: 0.7007652	total: 164ms	remaining: 604ms
214:	learn: 0.7002112	total: 165ms	remaining: 603ms
215:	learn: 0.6995721	total: 166ms	remaining: 603ms
216:	learn: 0.6993742	total: 167ms	remaining: 602ms
217:	learn: 0.6979339	total: 168ms	remaining: 601ms
218:	learn: 0.6973552	total: 168ms	remaining: 600ms
219:	learn: 0.6963199	total: 169ms	remaining: 599ms
220:	learn: 0.6955392	total: 170ms	remaining: 599ms
221:	learn: 0.6951172	total: 171ms	remaining: 598ms
222:	learn: 0.6944643	total: 171ms	remaining: 597ms
223:	learn: 0.6935388	total: 172ms	remaining: 596ms
224:	learn: 0.6924365	total: 173ms	remaining: 595ms
225:	learn: 0.6919358	total: 174ms	remaining: 594ms
226:	learn: 0.6909278	total: 174ms	remaining: 593ms
227:	learn: 0.6904753	total: 175ms	remaining: 592ms
228:	learn: 0.6896132	total: 176ms	remaining: 592ms
229:	learn: 0.6893358	total: 176ms	remaining: 591ms
230:	learn: 0.6887291	total: 177ms	remaining: 590ms
231:	learn: 0.6884614	total: 178ms	remaining: 589ms
232:	learn: 0.6878196	total: 179ms	remaining: 588ms
233:	learn: 0.6873639	total: 179ms	remaining: 587ms
234:	learn: 0.6864410	total: 180ms	remaining: 586ms
235:	learn: 0.6855452	total: 181ms	remaining: 586ms
236:	learn: 0.6851808	total: 182ms	remaining: 585ms
237:	learn: 0.6843190	total: 182ms	remaining: 584ms
238:	learn: 0.6831560	total: 183ms	remaining: 583ms
239:	learn: 0.6817169	total: 184ms	remaining: 582ms
240:	learn: 0.6807127	total: 185ms	remaining: 582ms
241:	learn: 0.6804081	total: 185ms	remaining: 581ms
242:	learn: 0.6797019	total: 186ms	remaining: 580ms
243:	learn: 0.6791179	total: 187ms	remaining: 579ms
244:	learn: 0.6787500	total: 188ms	remaining: 578ms
245:	learn: 0.6776437	total: 189ms	remaining: 579ms
246:	learn: 0.6769675	total: 190ms	remaining: 578ms
247:	learn: 0.6759556	total: 191ms	remaining: 578ms
248:	learn: 0.6753846	total: 191ms	remaining: 577ms
249:	learn: 0.6751012	total: 192ms	remaining: 577ms
250:	learn: 0.6745101	total: 193ms	remaining: 576ms
251:	learn: 0.6739573	total: 194ms	remaining: 576ms
252:	learn: 0.6735896	total: 195ms	remaining: 575ms
253:	learn: 0.6732270	total: 196ms	remaining: 575ms
254:	learn: 0.6723862	total: 196ms	remaining: 574ms
255:	learn: 0.6722007	total: 197ms	remaining: 573ms
256:	learn: 0.6712769	total: 198ms	remaining: 572ms
257:	learn: 0.6700596	total: 199ms	remaining: 572ms
258:	learn: 0.6696207	total: 200ms	remaining: 571ms
259:	learn: 0.6683192	total: 200ms	remaining: 570ms
260:	learn: 0.6672915	total: 201ms	remaining: 570ms
261:	learn: 0.6667259	total: 202ms	remaining: 570ms
262:	learn: 0.6650321	total: 203ms	remaining: 569ms
263:	learn: 0.6634881	total: 204ms	remaining: 568ms
264:	learn: 0.6630281	total: 205ms	remaining: 567ms
265:	learn: 0.6628088	total: 205ms	remaining: 567ms
266:	learn: 0.6616065	total: 206ms	remaining: 566ms
267:	learn: 0.6603164	total: 207ms	remaining: 565ms
268:	learn: 0.6594573	total: 208ms	remaining: 564ms
269:	learn: 0.6583596	total: 209ms	remaining: 564ms
270:	learn: 0.6568936	total: 209ms	remaining: 563ms
271:	learn: 0.6555925	total: 210ms	remaining: 563ms
272:	learn: 0.6544420	total: 211ms	remaining: 563ms
273:	learn: 0.6536708	total: 212ms	remaining: 562ms
274:	learn: 0.6527002	total: 213ms	remaining: 562ms
275:	learn: 0.6520870	total: 214ms	remaining: 562ms
276:	learn: 0.6508818	total: 215ms	remaining: 561ms
277:	learn: 0.6498027	total: 216ms	remaining: 561ms
278:	learn: 0.6488671	total: 217ms	remaining: 560ms
279:	learn: 0.6473936	total: 218ms	remaining: 560ms
280:	learn: 0.6469837	total: 219ms	remaining: 559ms
281:	learn: 0.6456318	total: 219ms	remaining: 559ms
282:	learn: 0.6447343	total: 220ms	remaining: 558ms
283:	learn: 0.6438943	total: 221ms	remaining: 557ms
284:	learn: 0.6434280	total: 222ms	remaining: 557ms
285:	learn: 0.6429900	total: 223ms	remaining: 556ms
286:	learn: 0.6425564	total: 224ms	remaining: 556ms
287:	learn: 0.6416747	total: 224ms	remaining: 555ms
288:	learn: 0.6413547	total: 225ms	remaining: 554ms
289:	learn: 0.6407748	total: 226ms	remaining: 553ms
290:	learn: 0.6403788	total: 227ms	remaining: 553ms
291:	learn: 0.6399705	total: 228ms	remaining: 552ms
292:	learn: 0.6394865	total: 228ms	remaining: 551ms
293:	learn: 0.6378668	total: 229ms	remaining: 551ms
294:	learn: 0.6368868	total: 230ms	remaining: 550ms
295:	learn: 0.6359676	total: 231ms	remaining: 549ms
296:	learn: 0.6353452	total: 232ms	remaining: 548ms
297:	learn: 0.6349586	total: 232ms	remaining: 548ms
298:	learn: 0.6342799	total: 233ms	remaining: 547ms
299:	learn: 0.6331847	total: 234ms	remaining: 547ms
300:	learn: 0.6322514	total: 235ms	remaining: 546ms
301:	learn: 0.6319585	total: 236ms	remaining: 545ms
302:	learn: 0.6304699	total: 237ms	remaining: 544ms
303:	learn: 0.6298205	total: 238ms	remaining: 544ms
304:	learn: 0.6289665	total: 238ms	remaining: 543ms
305:	learn: 0.6278627	total: 239ms	remaining: 543ms
306:	learn: 0.6265922	total: 240ms	remaining: 542ms
307:	learn: 0.6263300	total: 241ms	remaining: 541ms
308:	learn: 0.6254188	total: 242ms	remaining: 541ms
309:	learn: 0.6242653	total: 243ms	remaining: 540ms
310:	learn: 0.6231040	total: 244ms	remaining: 540ms
311:	learn: 0.6228468	total: 244ms	remaining: 539ms
312:	learn: 0.6225224	total: 245ms	remaining: 538ms
313:	learn: 0.6218699	total: 246ms	remaining: 537ms
314:	learn: 0.6208004	total: 247ms	remaining: 537ms
315:	learn: 0.6205352	total: 248ms	remaining: 536ms
316:	learn: 0.6200510	total: 248ms	remaining: 535ms
317:	learn: 0.6194674	total: 249ms	remaining: 534ms
318:	learn: 0.6189346	total: 250ms	remaining: 533ms
319:	learn: 0.6182479	total: 251ms	remaining: 533ms
320:	learn: 0.6179729	total: 251ms	remaining: 532ms
321:	learn: 0.6175584	total: 252ms	remaining: 531ms
322:	learn: 0.6164681	total: 253ms	remaining: 530ms
323:	learn: 0.6158471	total: 254ms	remaining: 529ms
324:	learn: 0.6148885	total: 254ms	remaining: 528ms
325:	learn: 0.6144352	total: 255ms	remaining: 528ms
326:	learn: 0.6132542	total: 256ms	remaining: 527ms
327:	learn: 0.6126162	total: 257ms	remaining: 526ms
328:	learn: 0.6113999	total: 257ms	remaining: 525ms
329:	learn: 0.6110660	total: 258ms	remaining: 524ms
330:	learn: 0.6099162	total: 259ms	remaining: 523ms
331:	learn: 0.6092256	total: 260ms	remaining: 523ms
332:	learn: 0.6082292	total: 261ms	remaining: 522ms
333:	learn: 0.6074560	total: 261ms	remaining: 521ms
334:	learn: 0.6073257	total: 262ms	remaining: 520ms
335:	learn: 0.6070780	total: 263ms	remaining: 519ms
336:	learn: 0.6060242	total: 263ms	remaining: 518ms
337:	learn: 0.6051546	total: 264ms	remaining: 518ms
338:	learn: 0.6045684	total: 265ms	remaining: 517ms
339:	learn: 0.6037820	total: 266ms	remaining: 516ms
340:	learn: 0.6034047	total: 267ms	remaining: 515ms
341:	learn: 0.6031593	total: 267ms	remaining: 514ms
342:	learn: 0.6025038	total: 268ms	remaining: 513ms
343:	learn: 0.6020045	total: 269ms	remaining: 513ms
344:	learn: 0.6004457	total: 270ms	remaining: 512ms
345:	learn: 0.5995922	total: 270ms	remaining: 511ms
346:	learn: 0.5992594	total: 271ms	remaining: 510ms
347:	learn: 0.5986312	total: 272ms	remaining: 509ms
348:	learn: 0.5981827	total: 272ms	remaining: 508ms
349:	learn: 0.5970112	total: 273ms	remaining: 507ms
350:	learn: 0.5968205	total: 274ms	remaining: 507ms
351:	learn: 0.5961103	total: 275ms	remaining: 506ms
352:	learn: 0.5959499	total: 276ms	remaining: 505ms
353:	learn: 0.5952879	total: 276ms	remaining: 504ms
354:	learn: 0.5951146	total: 277ms	remaining: 503ms
355:	learn: 0.5948080	total: 278ms	remaining: 502ms
356:	learn: 0.5940936	total: 278ms	remaining: 502ms
357:	learn: 0.5934490	total: 279ms	remaining: 501ms
358:	learn: 0.5919653	total: 280ms	remaining: 500ms
359:	learn: 0.5907205	total: 281ms	remaining: 499ms
360:	learn: 0.5901226	total: 281ms	remaining: 498ms
361:	learn: 0.5893279	total: 282ms	remaining: 497ms
362:	learn: 0.5889119	total: 283ms	remaining: 497ms
363:	learn: 0.5887241	total: 284ms	remaining: 496ms
364:	learn: 0.5885459	total: 284ms	remaining: 495ms
365:	learn: 0.5876433	total: 285ms	remaining: 494ms
366:	learn: 0.5874680	total: 286ms	remaining: 493ms
367:	learn: 0.5863292	total: 287ms	remaining: 492ms
368:	learn: 0.5857596	total: 287ms	remaining: 492ms
369:	learn: 0.5851366	total: 288ms	remaining: 491ms
370:	learn: 0.5839880	total: 289ms	remaining: 490ms
371:	learn: 0.5834235	total: 290ms	remaining: 489ms
372:	learn: 0.5819896	total: 290ms	remaining: 488ms
373:	learn: 0.5815065	total: 291ms	remaining: 487ms
374:	learn: 0.5805742	total: 292ms	remaining: 486ms
375:	learn: 0.5796932	total: 293ms	remaining: 486ms
376:	learn: 0.5795645	total: 293ms	remaining: 485ms
377:	learn: 0.5785786	total: 294ms	remaining: 484ms
378:	learn: 0.5777001	total: 295ms	remaining: 483ms
379:	learn: 0.5775332	total: 296ms	remaining: 482ms
380:	learn: 0.5767787	total: 296ms	remaining: 481ms
381:	learn: 0.5764085	total: 297ms	remaining: 481ms
382:	learn: 0.5757094	total: 298ms	remaining: 480ms
383:	learn: 0.5746808	total: 299ms	remaining: 479ms
384:	learn: 0.5732201	total: 299ms	remaining: 478ms
385:	learn: 0.5729884	total: 300ms	remaining: 477ms
386:	learn: 0.5722055	total: 301ms	remaining: 476ms
387:	learn: 0.5708254	total: 302ms	remaining: 476ms
388:	learn: 0.5703490	total: 302ms	remaining: 475ms
389:	learn: 0.5702327	total: 303ms	remaining: 474ms
390:	learn: 0.5696887	total: 304ms	remaining: 473ms
391:	learn: 0.5688100	total: 305ms	remaining: 472ms
392:	learn: 0.5676149	total: 305ms	remaining: 472ms
393:	learn: 0.5668555	total: 306ms	remaining: 471ms
394:	learn: 0.5664803	total: 307ms	remaining: 470ms
395:	learn: 0.5658793	total: 308ms	remaining: 469ms
396:	learn: 0.5654547	total: 308ms	remaining: 468ms
397:	learn: 0.5640169	total: 309ms	remaining: 467ms
398:	learn: 0.5632782	total: 310ms	remaining: 467ms
399:	learn: 0.5630709	total: 311ms	remaining: 466ms
400:	learn: 0.5625864	total: 311ms	remaining: 465ms
401:	learn: 0.5617902	total: 312ms	remaining: 464ms
402:	learn: 0.5610303	total: 313ms	remaining: 463ms
403:	learn: 0.5607191	total: 314ms	remaining: 463ms
404:	learn: 0.5601749	total: 314ms	remaining: 462ms
405:	learn: 0.5594208	total: 315ms	remaining: 461ms
406:	learn: 0.5588626	total: 316ms	remaining: 460ms
407:	learn: 0.5580659	total: 317ms	remaining: 459ms
408:	learn: 0.5572618	total: 317ms	remaining: 458ms
409:	learn: 0.5567896	total: 318ms	remaining: 458ms
410:	learn: 0.5566645	total: 319ms	remaining: 457ms
411:	learn: 0.5559420	total: 320ms	remaining: 456ms
412:	learn: 0.5552306	total: 320ms	remaining: 455ms
413:	learn: 0.5544838	total: 321ms	remaining: 454ms
414:	learn: 0.5535718	total: 322ms	remaining: 454ms
415:	learn: 0.5527552	total: 323ms	remaining: 453ms
416:	learn: 0.5526221	total: 323ms	remaining: 452ms
417:	learn: 0.5522856	total: 324ms	remaining: 451ms
418:	learn: 0.5514045	total: 325ms	remaining: 450ms
419:	learn: 0.5503757	total: 325ms	remaining: 449ms
420:	learn: 0.5499457	total: 326ms	remaining: 449ms
421:	learn: 0.5494998	total: 327ms	remaining: 448ms
422:	learn: 0.5489271	total: 328ms	remaining: 447ms
423:	learn: 0.5482921	total: 329ms	remaining: 446ms
424:	learn: 0.5474607	total: 329ms	remaining: 445ms
425:	learn: 0.5471489	total: 330ms	remaining: 445ms
426:	learn: 0.5459438	total: 331ms	remaining: 444ms
427:	learn: 0.5452187	total: 332ms	remaining: 443ms
428:	learn: 0.5449689	total: 332ms	remaining: 442ms
429:	learn: 0.5441072	total: 333ms	remaining: 441ms
430:	learn: 0.5438990	total: 334ms	remaining: 441ms
431:	learn: 0.5432885	total: 335ms	remaining: 440ms
432:	learn: 0.5424709	total: 335ms	remaining: 439ms
433:	learn: 0.5423167	total: 336ms	remaining: 438ms
434:	learn: 0.5415099	total: 337ms	remaining: 437ms
435:	learn: 0.5407482	total: 338ms	remaining: 437ms
436:	learn: 0.5405624	total: 338ms	remaining: 436ms
437:	learn: 0.5404652	total: 339ms	remaining: 435ms
438:	learn: 0.5391950	total: 340ms	remaining: 434ms
439:	learn: 0.5380609	total: 340ms	remaining: 433ms
440:	learn: 0.5377940	total: 341ms	remaining: 433ms
441:	learn: 0.5370516	total: 342ms	remaining: 432ms
442:	learn: 0.5361220	total: 343ms	remaining: 431ms
443:	learn: 0.5360225	total: 343ms	remaining: 430ms
444:	learn: 0.5353768	total: 344ms	remaining: 429ms
445:	learn: 0.5349615	total: 345ms	remaining: 428ms
446:	learn: 0.5340336	total: 346ms	remaining: 428ms
447:	learn: 0.5329500	total: 347ms	remaining: 427ms
448:	learn: 0.5325242	total: 347ms	remaining: 426ms
449:	learn: 0.5320743	total: 348ms	remaining: 425ms
450:	learn: 0.5313947	total: 349ms	remaining: 425ms
451:	learn: 0.5307477	total: 350ms	remaining: 424ms
452:	learn: 0.5298880	total: 350ms	remaining: 423ms
453:	learn: 0.5293664	total: 351ms	remaining: 422ms
454:	learn: 0.5288110	total: 352ms	remaining: 422ms
455:	learn: 0.5283207	total: 353ms	remaining: 421ms
456:	learn: 0.5277959	total: 354ms	remaining: 420ms
457:	learn: 0.5273212	total: 354ms	remaining: 419ms
458:	learn: 0.5265794	total: 355ms	remaining: 419ms
459:	learn: 0.5254606	total: 356ms	remaining: 418ms
460:	learn: 0.5249079	total: 357ms	remaining: 417ms
461:	learn: 0.5246454	total: 357ms	remaining: 416ms
462:	learn: 0.5243381	total: 358ms	remaining: 415ms
463:	learn: 0.5237485	total: 359ms	remaining: 415ms
464:	learn: 0.5234487	total: 360ms	remaining: 414ms
465:	learn: 0.5230185	total: 360ms	remaining: 413ms
466:	learn: 0.5227502	total: 361ms	remaining: 412ms
467:	learn: 0.5218839	total: 362ms	remaining: 411ms
468:	learn: 0.5213355	total: 363ms	remaining: 411ms
469:	learn: 0.5210133	total: 363ms	remaining: 410ms
470:	learn: 0.5205126	total: 364ms	remaining: 409ms
471:	learn: 0.5198566	total: 365ms	remaining: 408ms
472:	learn: 0.5192883	total: 366ms	remaining: 407ms
473:	learn: 0.5185794	total: 366ms	remaining: 407ms
474:	learn: 0.5179375	total: 367ms	remaining: 406ms
475:	learn: 0.5178401	total: 368ms	remaining: 405ms
476:	learn: 0.5171584	total: 369ms	remaining: 404ms
477:	learn: 0.5167799	total: 369ms	remaining: 403ms
478:	learn: 0.5162518	total: 370ms	remaining: 403ms
479:	learn: 0.5160130	total: 371ms	remaining: 402ms
480:	learn: 0.5159039	total: 372ms	remaining: 401ms
481:	learn: 0.5153099	total: 372ms	remaining: 400ms
482:	learn: 0.5147733	total: 373ms	remaining: 399ms
483:	learn: 0.5144933	total: 374ms	remaining: 399ms
484:	learn: 0.5142764	total: 375ms	remaining: 398ms
485:	learn: 0.5138561	total: 376ms	remaining: 397ms
486:	learn: 0.5131746	total: 377ms	remaining: 397ms
487:	learn: 0.5117346	total: 377ms	remaining: 396ms
488:	learn: 0.5116685	total: 378ms	remaining: 395ms
489:	learn: 0.5105671	total: 379ms	remaining: 394ms
490:	learn: 0.5097161	total: 380ms	remaining: 394ms
491:	learn: 0.5087269	total: 381ms	remaining: 393ms
492:	learn: 0.5078983	total: 381ms	remaining: 392ms
493:	learn: 0.5072933	total: 382ms	remaining: 391ms
494:	learn: 0.5070132	total: 383ms	remaining: 391ms
495:	learn: 0.5068664	total: 384ms	remaining: 390ms
496:	learn: 0.5063680	total: 384ms	remaining: 389ms
497:	learn: 0.5062266	total: 385ms	remaining: 388ms
498:	learn: 0.5055700	total: 386ms	remaining: 388ms
499:	learn: 0.5045557	total: 387ms	remaining: 387ms
500:	learn: 0.5043232	total: 388ms	remaining: 386ms
501:	learn: 0.5032844	total: 388ms	remaining: 385ms
502:	learn: 0.5024221	total: 389ms	remaining: 385ms
503:	learn: 0.5017647	total: 390ms	remaining: 384ms
504:	learn: 0.5009892	total: 391ms	remaining: 383ms
505:	learn: 0.5003844	total: 392ms	remaining: 382ms
506:	learn: 0.4998939	total: 392ms	remaining: 382ms
507:	learn: 0.4994395	total: 393ms	remaining: 381ms
508:	learn: 0.4990071	total: 394ms	remaining: 380ms
509:	learn: 0.4989153	total: 395ms	remaining: 380ms
510:	learn: 0.4985564	total: 396ms	remaining: 379ms
511:	learn: 0.4984507	total: 397ms	remaining: 378ms
512:	learn: 0.4981224	total: 398ms	remaining: 377ms
513:	learn: 0.4973598	total: 398ms	remaining: 377ms
514:	learn: 0.4971925	total: 399ms	remaining: 376ms
515:	learn: 0.4963132	total: 400ms	remaining: 376ms
516:	learn: 0.4962383	total: 401ms	remaining: 375ms
517:	learn: 0.4951988	total: 402ms	remaining: 374ms
518:	learn: 0.4944622	total: 403ms	remaining: 373ms
519:	learn: 0.4936164	total: 403ms	remaining: 372ms
520:	learn: 0.4934560	total: 404ms	remaining: 372ms
521:	learn: 0.4928034	total: 405ms	remaining: 371ms
522:	learn: 0.4924159	total: 406ms	remaining: 370ms
523:	learn: 0.4921147	total: 407ms	remaining: 369ms
524:	learn: 0.4920188	total: 407ms	remaining: 369ms
525:	learn: 0.4917761	total: 408ms	remaining: 368ms
526:	learn: 0.4913254	total: 409ms	remaining: 367ms
527:	learn: 0.4909685	total: 410ms	remaining: 366ms
528:	learn: 0.4898065	total: 411ms	remaining: 366ms
529:	learn: 0.4890168	total: 411ms	remaining: 365ms
530:	learn: 0.4883761	total: 412ms	remaining: 364ms
531:	learn: 0.4873646	total: 413ms	remaining: 363ms
532:	learn: 0.4869453	total: 414ms	remaining: 362ms
533:	learn: 0.4865142	total: 414ms	remaining: 362ms
534:	learn: 0.4855349	total: 415ms	remaining: 361ms
535:	learn: 0.4852726	total: 416ms	remaining: 360ms
536:	learn: 0.4845198	total: 417ms	remaining: 359ms
537:	learn: 0.4840355	total: 418ms	remaining: 359ms
538:	learn: 0.4836599	total: 418ms	remaining: 358ms
539:	learn: 0.4829054	total: 419ms	remaining: 357ms
540:	learn: 0.4825951	total: 420ms	remaining: 356ms
541:	learn: 0.4821082	total: 421ms	remaining: 356ms
542:	learn: 0.4818599	total: 422ms	remaining: 355ms
543:	learn: 0.4808133	total: 423ms	remaining: 354ms
544:	learn: 0.4803486	total: 423ms	remaining: 354ms
545:	learn: 0.4797681	total: 424ms	remaining: 353ms
546:	learn: 0.4791221	total: 425ms	remaining: 352ms
547:	learn: 0.4785300	total: 426ms	remaining: 351ms
548:	learn: 0.4782198	total: 426ms	remaining: 350ms
549:	learn: 0.4773603	total: 427ms	remaining: 349ms
550:	learn: 0.4770909	total: 428ms	remaining: 349ms
551:	learn: 0.4768665	total: 429ms	remaining: 348ms
552:	learn: 0.4759941	total: 430ms	remaining: 347ms
553:	learn: 0.4757538	total: 430ms	remaining: 346ms
554:	learn: 0.4756811	total: 431ms	remaining: 346ms
555:	learn: 0.4753084	total: 432ms	remaining: 345ms
556:	learn: 0.4751085	total: 433ms	remaining: 344ms
557:	learn: 0.4745219	total: 433ms	remaining: 343ms
558:	learn: 0.4744605	total: 434ms	remaining: 342ms
559:	learn: 0.4739367	total: 435ms	remaining: 342ms
560:	learn: 0.4731250	total: 436ms	remaining: 341ms
561:	learn: 0.4726886	total: 436ms	remaining: 340ms
562:	learn: 0.4720739	total: 437ms	remaining: 339ms
563:	learn: 0.4713770	total: 438ms	remaining: 338ms
564:	learn: 0.4707313	total: 439ms	remaining: 338ms
565:	learn: 0.4702300	total: 439ms	remaining: 337ms
566:	learn: 0.4696829	total: 440ms	remaining: 336ms
567:	learn: 0.4692632	total: 441ms	remaining: 335ms
568:	learn: 0.4682183	total: 442ms	remaining: 335ms
569:	learn: 0.4677771	total: 443ms	remaining: 334ms
570:	learn: 0.4671408	total: 444ms	remaining: 333ms
571:	learn: 0.4668011	total: 445ms	remaining: 333ms
572:	learn: 0.4660358	total: 445ms	remaining: 332ms
573:	learn: 0.4656981	total: 446ms	remaining: 331ms
574:	learn: 0.4652003	total: 447ms	remaining: 330ms
575:	learn: 0.4649393	total: 448ms	remaining: 329ms
576:	learn: 0.4641978	total: 448ms	remaining: 329ms
577:	learn: 0.4638818	total: 449ms	remaining: 328ms
578:	learn: 0.4636491	total: 450ms	remaining: 327ms
579:	learn: 0.4634072	total: 451ms	remaining: 326ms
580:	learn: 0.4627444	total: 452ms	remaining: 326ms
581:	learn: 0.4624471	total: 452ms	remaining: 325ms
582:	learn: 0.4621546	total: 453ms	remaining: 324ms
583:	learn: 0.4616977	total: 454ms	remaining: 323ms
584:	learn: 0.4607791	total: 455ms	remaining: 323ms
585:	learn: 0.4605421	total: 456ms	remaining: 322ms
586:	learn: 0.4604642	total: 456ms	remaining: 321ms
587:	learn: 0.4597668	total: 457ms	remaining: 320ms
588:	learn: 0.4594560	total: 458ms	remaining: 320ms
589:	learn: 0.4592168	total: 459ms	remaining: 319ms
590:	learn: 0.4591496	total: 460ms	remaining: 318ms
591:	learn: 0.4590768	total: 460ms	remaining: 317ms
592:	learn: 0.4583855	total: 461ms	remaining: 316ms
593:	learn: 0.4582407	total: 462ms	remaining: 316ms
594:	learn: 0.4579812	total: 463ms	remaining: 315ms
595:	learn: 0.4578129	total: 463ms	remaining: 314ms
596:	learn: 0.4574519	total: 464ms	remaining: 313ms
597:	learn: 0.4564839	total: 465ms	remaining: 312ms
598:	learn: 0.4557686	total: 466ms	remaining: 312ms
599:	learn: 0.4550995	total: 466ms	remaining: 311ms
600:	learn: 0.4549605	total: 467ms	remaining: 310ms
601:	learn: 0.4544469	total: 468ms	remaining: 309ms
602:	learn: 0.4537660	total: 469ms	remaining: 309ms
603:	learn: 0.4535725	total: 469ms	remaining: 308ms
604:	learn: 0.4528622	total: 470ms	remaining: 307ms
605:	learn: 0.4524100	total: 471ms	remaining: 306ms
606:	learn: 0.4523632	total: 472ms	remaining: 305ms
607:	learn: 0.4514765	total: 472ms	remaining: 305ms
608:	learn: 0.4513858	total: 473ms	remaining: 304ms
609:	learn: 0.4505026	total: 474ms	remaining: 303ms
610:	learn: 0.4499173	total: 475ms	remaining: 302ms
611:	learn: 0.4494225	total: 475ms	remaining: 301ms
612:	learn: 0.4493433	total: 476ms	remaining: 301ms
613:	learn: 0.4489980	total: 477ms	remaining: 300ms
614:	learn: 0.4485107	total: 478ms	remaining: 299ms
615:	learn: 0.4482914	total: 478ms	remaining: 298ms
616:	learn: 0.4479824	total: 479ms	remaining: 297ms
617:	learn: 0.4476672	total: 480ms	remaining: 297ms
618:	learn: 0.4475792	total: 481ms	remaining: 296ms
619:	learn: 0.4469041	total: 481ms	remaining: 295ms
620:	learn: 0.4468097	total: 482ms	remaining: 294ms
621:	learn: 0.4462448	total: 483ms	remaining: 293ms
622:	learn: 0.4455773	total: 484ms	remaining: 293ms
623:	learn: 0.4452743	total: 484ms	remaining: 292ms
624:	learn: 0.4449669	total: 485ms	remaining: 291ms
625:	learn: 0.4449107	total: 486ms	remaining: 290ms
626:	learn: 0.4445103	total: 487ms	remaining: 289ms
627:	learn: 0.4439626	total: 487ms	remaining: 289ms
628:	learn: 0.4437854	total: 488ms	remaining: 288ms
629:	learn: 0.4435697	total: 489ms	remaining: 287ms
630:	learn: 0.4427289	total: 490ms	remaining: 286ms
631:	learn: 0.4424854	total: 490ms	remaining: 285ms
632:	learn: 0.4419003	total: 491ms	remaining: 285ms
633:	learn: 0.4413421	total: 492ms	remaining: 284ms
634:	learn: 0.4411563	total: 493ms	remaining: 283ms
635:	learn: 0.4407863	total: 493ms	remaining: 282ms
636:	learn: 0.4405971	total: 494ms	remaining: 281ms
637:	learn: 0.4399681	total: 495ms	remaining: 281ms
638:	learn: 0.4391820	total: 495ms	remaining: 280ms
639:	learn: 0.4391098	total: 496ms	remaining: 279ms
640:	learn: 0.4389980	total: 497ms	remaining: 278ms
641:	learn: 0.4388069	total: 498ms	remaining: 277ms
642:	learn: 0.4385053	total: 498ms	remaining: 277ms
643:	learn: 0.4381924	total: 499ms	remaining: 276ms
644:	learn: 0.4380684	total: 500ms	remaining: 275ms
645:	learn: 0.4377361	total: 501ms	remaining: 274ms
646:	learn: 0.4374485	total: 501ms	remaining: 274ms
647:	learn: 0.4367302	total: 502ms	remaining: 273ms
648:	learn: 0.4365484	total: 503ms	remaining: 272ms
649:	learn: 0.4361076	total: 504ms	remaining: 271ms
650:	learn: 0.4355559	total: 504ms	remaining: 270ms
651:	learn: 0.4349796	total: 505ms	remaining: 270ms
652:	learn: 0.4348702	total: 506ms	remaining: 269ms
653:	learn: 0.4347680	total: 507ms	remaining: 268ms
654:	learn: 0.4345384	total: 507ms	remaining: 267ms
655:	learn: 0.4343610	total: 508ms	remaining: 266ms
656:	learn: 0.4337979	total: 509ms	remaining: 266ms
657:	learn: 0.4334507	total: 510ms	remaining: 265ms
658:	learn: 0.4331041	total: 510ms	remaining: 264ms
659:	learn: 0.4326676	total: 511ms	remaining: 263ms
660:	learn: 0.4322375	total: 512ms	remaining: 263ms
661:	learn: 0.4321636	total: 513ms	remaining: 262ms
662:	learn: 0.4314121	total: 513ms	remaining: 261ms
663:	learn: 0.4312713	total: 514ms	remaining: 260ms
664:	learn: 0.4309760	total: 515ms	remaining: 259ms
665:	learn: 0.4306004	total: 516ms	remaining: 259ms
666:	learn: 0.4305024	total: 516ms	remaining: 258ms
667:	learn: 0.4299473	total: 517ms	remaining: 257ms
668:	learn: 0.4296533	total: 518ms	remaining: 256ms
669:	learn: 0.4292657	total: 519ms	remaining: 255ms
670:	learn: 0.4283430	total: 519ms	remaining: 255ms
671:	learn: 0.4280879	total: 520ms	remaining: 254ms
672:	learn: 0.4280044	total: 521ms	remaining: 253ms
673:	learn: 0.4279470	total: 522ms	remaining: 252ms
674:	learn: 0.4273315	total: 522ms	remaining: 252ms
675:	learn: 0.4272021	total: 523ms	remaining: 251ms
676:	learn: 0.4264297	total: 524ms	remaining: 250ms
677:	learn: 0.4256992	total: 525ms	remaining: 249ms
678:	learn: 0.4256250	total: 525ms	remaining: 248ms
679:	learn: 0.4250333	total: 526ms	remaining: 248ms
680:	learn: 0.4246208	total: 527ms	remaining: 247ms
681:	learn: 0.4244598	total: 528ms	remaining: 246ms
682:	learn: 0.4239100	total: 528ms	remaining: 245ms
683:	learn: 0.4231483	total: 529ms	remaining: 244ms
684:	learn: 0.4227670	total: 530ms	remaining: 244ms
685:	learn: 0.4226944	total: 530ms	remaining: 243ms
686:	learn: 0.4224509	total: 531ms	remaining: 242ms
687:	learn: 0.4217300	total: 532ms	remaining: 241ms
688:	learn: 0.4215560	total: 533ms	remaining: 240ms
689:	learn: 0.4214951	total: 533ms	remaining: 240ms
690:	learn: 0.4213332	total: 534ms	remaining: 239ms
691:	learn: 0.4207583	total: 535ms	remaining: 238ms
692:	learn: 0.4205507	total: 536ms	remaining: 237ms
693:	learn: 0.4203066	total: 536ms	remaining: 236ms
694:	learn: 0.4197750	total: 537ms	remaining: 236ms
695:	learn: 0.4191003	total: 538ms	remaining: 235ms
696:	learn: 0.4183181	total: 539ms	remaining: 234ms
697:	learn: 0.4180857	total: 539ms	remaining: 233ms
698:	learn: 0.4176200	total: 540ms	remaining: 233ms
699:	learn: 0.4171842	total: 541ms	remaining: 232ms
700:	learn: 0.4167196	total: 541ms	remaining: 231ms
701:	learn: 0.4166221	total: 542ms	remaining: 230ms
702:	learn: 0.4161130	total: 543ms	remaining: 229ms
703:	learn: 0.4159992	total: 544ms	remaining: 229ms
704:	learn: 0.4158702	total: 544ms	remaining: 228ms
705:	learn: 0.4152161	total: 545ms	remaining: 227ms
706:	learn: 0.4149008	total: 546ms	remaining: 226ms
707:	learn: 0.4147037	total: 547ms	remaining: 225ms
708:	learn: 0.4143895	total: 547ms	remaining: 225ms
709:	learn: 0.4143075	total: 548ms	remaining: 224ms
710:	learn: 0.4141207	total: 549ms	remaining: 223ms
711:	learn: 0.4139193	total: 550ms	remaining: 222ms
712:	learn: 0.4134656	total: 550ms	remaining: 222ms
713:	learn: 0.4129482	total: 551ms	remaining: 221ms
714:	learn: 0.4127054	total: 552ms	remaining: 220ms
715:	learn: 0.4122484	total: 553ms	remaining: 219ms
716:	learn: 0.4116536	total: 553ms	remaining: 218ms
717:	learn: 0.4115340	total: 554ms	remaining: 218ms
718:	learn: 0.4111749	total: 555ms	remaining: 217ms
719:	learn: 0.4111355	total: 556ms	remaining: 216ms
720:	learn: 0.4106749	total: 556ms	remaining: 215ms
721:	learn: 0.4105087	total: 557ms	remaining: 214ms
722:	learn: 0.4104449	total: 558ms	remaining: 214ms
723:	learn: 0.4103588	total: 559ms	remaining: 213ms
724:	learn: 0.4100375	total: 559ms	remaining: 212ms
725:	learn: 0.4098488	total: 560ms	remaining: 211ms
726:	learn: 0.4093508	total: 561ms	remaining: 211ms
727:	learn: 0.4089628	total: 561ms	remaining: 210ms
728:	learn: 0.4089023	total: 563ms	remaining: 209ms
729:	learn: 0.4087204	total: 563ms	remaining: 208ms
730:	learn: 0.4085262	total: 564ms	remaining: 208ms
731:	learn: 0.4080462	total: 565ms	remaining: 207ms
732:	learn: 0.4079081	total: 566ms	remaining: 206ms
733:	learn: 0.4078606	total: 567ms	remaining: 205ms
734:	learn: 0.4073632	total: 568ms	remaining: 205ms
735:	learn: 0.4072483	total: 568ms	remaining: 204ms
736:	learn: 0.4068147	total: 569ms	remaining: 203ms
737:	learn: 0.4067721	total: 570ms	remaining: 202ms
738:	learn: 0.4061628	total: 571ms	remaining: 202ms
739:	learn: 0.4054225	total: 572ms	remaining: 201ms
740:	learn: 0.4051898	total: 572ms	remaining: 200ms
741:	learn: 0.4047733	total: 573ms	remaining: 199ms
742:	learn: 0.4047267	total: 574ms	remaining: 199ms
743:	learn: 0.4044731	total: 575ms	remaining: 198ms
744:	learn: 0.4037698	total: 576ms	remaining: 197ms
745:	learn: 0.4031171	total: 577ms	remaining: 196ms
746:	learn: 0.4030714	total: 577ms	remaining: 196ms
747:	learn: 0.4027456	total: 578ms	remaining: 195ms
748:	learn: 0.4022836	total: 579ms	remaining: 194ms
749:	learn: 0.4022435	total: 580ms	remaining: 193ms
750:	learn: 0.4019789	total: 581ms	remaining: 193ms
751:	learn: 0.4015978	total: 582ms	remaining: 192ms
752:	learn: 0.4012652	total: 582ms	remaining: 191ms
753:	learn: 0.4008450	total: 583ms	remaining: 190ms
754:	learn: 0.4004749	total: 584ms	remaining: 189ms
755:	learn: 0.3997901	total: 585ms	remaining: 189ms
756:	learn: 0.3994461	total: 586ms	remaining: 188ms
757:	learn: 0.3992808	total: 586ms	remaining: 187ms
758:	learn: 0.3987892	total: 587ms	remaining: 186ms
759:	learn: 0.3986003	total: 588ms	remaining: 186ms
760:	learn: 0.3985837	total: 589ms	remaining: 185ms
761:	learn: 0.3980021	total: 589ms	remaining: 184ms
762:	learn: 0.3972531	total: 590ms	remaining: 183ms
763:	learn: 0.3967450	total: 591ms	remaining: 183ms
764:	learn: 0.3962353	total: 592ms	remaining: 182ms
765:	learn: 0.3960842	total: 593ms	remaining: 181ms
766:	learn: 0.3958177	total: 593ms	remaining: 180ms
767:	learn: 0.3953818	total: 594ms	remaining: 179ms
768:	learn: 0.3950858	total: 595ms	remaining: 179ms
769:	learn: 0.3950597	total: 596ms	remaining: 178ms
770:	learn: 0.3950090	total: 596ms	remaining: 177ms
771:	learn: 0.3944948	total: 597ms	remaining: 176ms
772:	learn: 0.3940412	total: 598ms	remaining: 176ms
773:	learn: 0.3934408	total: 599ms	remaining: 175ms
774:	learn: 0.3930082	total: 600ms	remaining: 174ms
775:	learn: 0.3926642	total: 600ms	remaining: 173ms
776:	learn: 0.3923027	total: 601ms	remaining: 173ms
777:	learn: 0.3919626	total: 602ms	remaining: 172ms
778:	learn: 0.3916876	total: 603ms	remaining: 171ms
779:	learn: 0.3912542	total: 603ms	remaining: 170ms
780:	learn: 0.3911640	total: 604ms	remaining: 169ms
781:	learn: 0.3908788	total: 605ms	remaining: 169ms
782:	learn: 0.3903531	total: 606ms	remaining: 168ms
783:	learn: 0.3899371	total: 607ms	remaining: 167ms
784:	learn: 0.3894597	total: 608ms	remaining: 166ms
785:	learn: 0.3890685	total: 608ms	remaining: 166ms
786:	learn: 0.3885804	total: 609ms	remaining: 165ms
787:	learn: 0.3877986	total: 610ms	remaining: 164ms
788:	learn: 0.3875574	total: 611ms	remaining: 163ms
789:	learn: 0.3873921	total: 611ms	remaining: 163ms
790:	learn: 0.3871179	total: 612ms	remaining: 162ms
791:	learn: 0.3866431	total: 613ms	remaining: 161ms
792:	learn: 0.3859897	total: 614ms	remaining: 160ms
793:	learn: 0.3853267	total: 615ms	remaining: 159ms
794:	learn: 0.3849801	total: 615ms	remaining: 159ms
795:	learn: 0.3849306	total: 616ms	remaining: 158ms
796:	learn: 0.3846657	total: 617ms	remaining: 157ms
797:	learn: 0.3842829	total: 618ms	remaining: 156ms
798:	learn: 0.3841567	total: 618ms	remaining: 156ms
799:	learn: 0.3838837	total: 619ms	remaining: 155ms
800:	learn: 0.3833496	total: 620ms	remaining: 154ms
801:	learn: 0.3825475	total: 621ms	remaining: 153ms
802:	learn: 0.3818179	total: 621ms	remaining: 152ms
803:	learn: 0.3813245	total: 622ms	remaining: 152ms
804:	learn: 0.3809286	total: 623ms	remaining: 151ms
805:	learn: 0.3805543	total: 624ms	remaining: 150ms
806:	learn: 0.3804323	total: 624ms	remaining: 149ms
807:	learn: 0.3803813	total: 625ms	remaining: 149ms
808:	learn: 0.3797826	total: 626ms	remaining: 148ms
809:	learn: 0.3793651	total: 627ms	remaining: 147ms
810:	learn: 0.3792305	total: 628ms	remaining: 146ms
811:	learn: 0.3788077	total: 628ms	remaining: 145ms
812:	learn: 0.3785799	total: 629ms	remaining: 145ms
813:	learn: 0.3783043	total: 630ms	remaining: 144ms
814:	learn: 0.3778900	total: 631ms	remaining: 143ms
815:	learn: 0.3776920	total: 631ms	remaining: 142ms
816:	learn: 0.3775013	total: 632ms	remaining: 142ms
817:	learn: 0.3771851	total: 633ms	remaining: 141ms
818:	learn: 0.3767246	total: 634ms	remaining: 140ms
819:	learn: 0.3766059	total: 634ms	remaining: 139ms
820:	learn: 0.3764735	total: 635ms	remaining: 139ms
821:	learn: 0.3759360	total: 636ms	remaining: 138ms
822:	learn: 0.3753616	total: 637ms	remaining: 137ms
823:	learn: 0.3751780	total: 637ms	remaining: 136ms
824:	learn: 0.3751283	total: 638ms	remaining: 135ms
825:	learn: 0.3748131	total: 639ms	remaining: 135ms
826:	learn: 0.3743360	total: 640ms	remaining: 134ms
827:	learn: 0.3742716	total: 640ms	remaining: 133ms
828:	learn: 0.3739736	total: 641ms	remaining: 132ms
829:	learn: 0.3736289	total: 642ms	remaining: 131ms
830:	learn: 0.3733438	total: 643ms	remaining: 131ms
831:	learn: 0.3728945	total: 643ms	remaining: 130ms
832:	learn: 0.3725370	total: 644ms	remaining: 129ms
833:	learn: 0.3724139	total: 645ms	remaining: 128ms
834:	learn: 0.3720242	total: 646ms	remaining: 128ms
835:	learn: 0.3717992	total: 647ms	remaining: 127ms
836:	learn: 0.3716397	total: 647ms	remaining: 126ms
837:	learn: 0.3715167	total: 648ms	remaining: 125ms
838:	learn: 0.3710690	total: 649ms	remaining: 125ms
839:	learn: 0.3710277	total: 650ms	remaining: 124ms
840:	learn: 0.3703244	total: 650ms	remaining: 123ms
841:	learn: 0.3702158	total: 651ms	remaining: 122ms
842:	learn: 0.3695900	total: 652ms	remaining: 121ms
843:	learn: 0.3691500	total: 653ms	remaining: 121ms
844:	learn: 0.3688786	total: 653ms	remaining: 120ms
845:	learn: 0.3685215	total: 654ms	remaining: 119ms
846:	learn: 0.3684022	total: 655ms	remaining: 118ms
847:	learn: 0.3681694	total: 656ms	remaining: 118ms
848:	learn: 0.3678587	total: 657ms	remaining: 117ms
849:	learn: 0.3673990	total: 657ms	remaining: 116ms
850:	learn: 0.3673482	total: 658ms	remaining: 115ms
851:	learn: 0.3672121	total: 659ms	remaining: 114ms
852:	learn: 0.3667634	total: 660ms	remaining: 114ms
853:	learn: 0.3665941	total: 660ms	remaining: 113ms
854:	learn: 0.3664468	total: 661ms	remaining: 112ms
855:	learn: 0.3662572	total: 662ms	remaining: 111ms
856:	learn: 0.3655806	total: 663ms	remaining: 111ms
857:	learn: 0.3653940	total: 663ms	remaining: 110ms
858:	learn: 0.3650892	total: 664ms	remaining: 109ms
859:	learn: 0.3647680	total: 665ms	remaining: 108ms
860:	learn: 0.3640736	total: 666ms	remaining: 107ms
861:	learn: 0.3639681	total: 666ms	remaining: 107ms
862:	learn: 0.3635414	total: 667ms	remaining: 106ms
863:	learn: 0.3631801	total: 668ms	remaining: 105ms
864:	learn: 0.3628413	total: 669ms	remaining: 104ms
865:	learn: 0.3626361	total: 670ms	remaining: 104ms
866:	learn: 0.3624668	total: 670ms	remaining: 103ms
867:	learn: 0.3623228	total: 671ms	remaining: 102ms
868:	learn: 0.3622717	total: 672ms	remaining: 101ms
869:	learn: 0.3620434	total: 672ms	remaining: 100ms
870:	learn: 0.3619626	total: 673ms	remaining: 99.7ms
871:	learn: 0.3616540	total: 674ms	remaining: 98.9ms
872:	learn: 0.3615363	total: 675ms	remaining: 98.2ms
873:	learn: 0.3610562	total: 676ms	remaining: 97.4ms
874:	learn: 0.3605780	total: 676ms	remaining: 96.6ms
875:	learn: 0.3600068	total: 677ms	remaining: 95.8ms
876:	learn: 0.3596207	total: 678ms	remaining: 95.1ms
877:	learn: 0.3594836	total: 679ms	remaining: 94.3ms
878:	learn: 0.3592012	total: 679ms	remaining: 93.5ms
879:	learn: 0.3590119	total: 680ms	remaining: 92.7ms
880:	learn: 0.3586686	total: 681ms	remaining: 92ms
881:	learn: 0.3585206	total: 682ms	remaining: 91.2ms
882:	learn: 0.3579825	total: 682ms	remaining: 90.4ms
883:	learn: 0.3576689	total: 683ms	remaining: 89.6ms
884:	learn: 0.3575129	total: 684ms	remaining: 88.9ms
885:	learn: 0.3573265	total: 685ms	remaining: 88.1ms
886:	learn: 0.3571407	total: 685ms	remaining: 87.3ms
887:	learn: 0.3571079	total: 686ms	remaining: 86.5ms
888:	learn: 0.3566820	total: 687ms	remaining: 85.8ms
889:	learn: 0.3566548	total: 688ms	remaining: 85ms
890:	learn: 0.3563844	total: 688ms	remaining: 84.2ms
891:	learn: 0.3558904	total: 689ms	remaining: 83.4ms
892:	learn: 0.3557448	total: 690ms	remaining: 82.7ms
893:	learn: 0.3556078	total: 691ms	remaining: 81.9ms
894:	learn: 0.3553531	total: 691ms	remaining: 81.1ms
895:	learn: 0.3550870	total: 692ms	remaining: 80.3ms
896:	learn: 0.3545962	total: 693ms	remaining: 79.6ms
897:	learn: 0.3539469	total: 694ms	remaining: 78.8ms
898:	learn: 0.3534989	total: 694ms	remaining: 78ms
899:	learn: 0.3532938	total: 695ms	remaining: 77.2ms
900:	learn: 0.3530047	total: 696ms	remaining: 76.5ms
901:	learn: 0.3528810	total: 697ms	remaining: 75.7ms
902:	learn: 0.3527541	total: 697ms	remaining: 74.9ms
903:	learn: 0.3521569	total: 698ms	remaining: 74.1ms
904:	learn: 0.3516488	total: 699ms	remaining: 73.4ms
905:	learn: 0.3511842	total: 700ms	remaining: 72.6ms
906:	learn: 0.3510145	total: 701ms	remaining: 71.8ms
907:	learn: 0.3508082	total: 701ms	remaining: 71.1ms
908:	learn: 0.3504204	total: 702ms	remaining: 70.3ms
909:	learn: 0.3502998	total: 703ms	remaining: 69.5ms
910:	learn: 0.3500299	total: 704ms	remaining: 68.8ms
911:	learn: 0.3496831	total: 705ms	remaining: 68ms
912:	learn: 0.3492594	total: 705ms	remaining: 67.2ms
913:	learn: 0.3490997	total: 706ms	remaining: 66.4ms
914:	learn: 0.3487512	total: 707ms	remaining: 65.7ms
915:	learn: 0.3487113	total: 708ms	remaining: 64.9ms
916:	learn: 0.3484987	total: 708ms	remaining: 64.1ms
917:	learn: 0.3482167	total: 709ms	remaining: 63.3ms
918:	learn: 0.3481162	total: 710ms	remaining: 62.6ms
919:	learn: 0.3480436	total: 711ms	remaining: 61.8ms
920:	learn: 0.3479042	total: 711ms	remaining: 61ms
921:	learn: 0.3475888	total: 712ms	remaining: 60.2ms
922:	learn: 0.3474941	total: 713ms	remaining: 59.5ms
923:	learn: 0.3472497	total: 714ms	remaining: 58.7ms
924:	learn: 0.3471594	total: 714ms	remaining: 57.9ms
925:	learn: 0.3471039	total: 715ms	remaining: 57.1ms
926:	learn: 0.3469437	total: 716ms	remaining: 56.4ms
927:	learn: 0.3467769	total: 717ms	remaining: 55.6ms
928:	learn: 0.3464622	total: 717ms	remaining: 54.8ms
929:	learn: 0.3459416	total: 718ms	remaining: 54ms
930:	learn: 0.3458893	total: 719ms	remaining: 53.3ms
931:	learn: 0.3456056	total: 720ms	remaining: 52.5ms
932:	learn: 0.3452029	total: 720ms	remaining: 51.7ms
933:	learn: 0.3447528	total: 721ms	remaining: 51ms
934:	learn: 0.3445469	total: 722ms	remaining: 50.2ms
935:	learn: 0.3444795	total: 723ms	remaining: 49.4ms
936:	learn: 0.3441240	total: 723ms	remaining: 48.6ms
937:	learn: 0.3437529	total: 724ms	remaining: 47.9ms
938:	learn: 0.3434793	total: 725ms	remaining: 47.1ms
939:	learn: 0.3433033	total: 726ms	remaining: 46.3ms
940:	learn: 0.3428987	total: 726ms	remaining: 45.5ms
941:	learn: 0.3427788	total: 727ms	remaining: 44.8ms
942:	learn: 0.3426929	total: 728ms	remaining: 44ms
943:	learn: 0.3423175	total: 729ms	remaining: 43.2ms
944:	learn: 0.3419903	total: 729ms	remaining: 42.5ms
945:	learn: 0.3419111	total: 730ms	remaining: 41.7ms
946:	learn: 0.3417859	total: 731ms	remaining: 40.9ms
947:	learn: 0.3416558	total: 732ms	remaining: 40.1ms
948:	learn: 0.3413930	total: 732ms	remaining: 39.4ms
949:	learn: 0.3409045	total: 733ms	remaining: 38.6ms
950:	learn: 0.3406349	total: 734ms	remaining: 37.8ms
951:	learn: 0.3404183	total: 735ms	remaining: 37ms
952:	learn: 0.3402783	total: 736ms	remaining: 36.3ms
953:	learn: 0.3401141	total: 736ms	remaining: 35.5ms
954:	learn: 0.3394943	total: 737ms	remaining: 34.7ms
955:	learn: 0.3391837	total: 738ms	remaining: 34ms
956:	learn: 0.3389535	total: 739ms	remaining: 33.2ms
957:	learn: 0.3387444	total: 739ms	remaining: 32.4ms
958:	learn: 0.3386766	total: 740ms	remaining: 31.6ms
959:	learn: 0.3380240	total: 741ms	remaining: 30.9ms
960:	learn: 0.3377472	total: 742ms	remaining: 30.1ms
961:	learn: 0.3375140	total: 743ms	remaining: 29.3ms
962:	learn: 0.3372070	total: 743ms	remaining: 28.6ms
963:	learn: 0.3370944	total: 744ms	remaining: 27.8ms
964:	learn: 0.3369636	total: 745ms	remaining: 27ms
965:	learn: 0.3367332	total: 746ms	remaining: 26.3ms
966:	learn: 0.3363269	total: 747ms	remaining: 25.5ms
967:	learn: 0.3362887	total: 747ms	remaining: 24.7ms
968:	learn: 0.3361236	total: 748ms	remaining: 23.9ms
969:	learn: 0.3358705	total: 749ms	remaining: 23.2ms
970:	learn: 0.3357516	total: 750ms	remaining: 22.4ms
971:	learn: 0.3353482	total: 751ms	remaining: 21.6ms
972:	learn: 0.3349115	total: 752ms	remaining: 20.9ms
973:	learn: 0.3347851	total: 753ms	remaining: 20.1ms
974:	learn: 0.3343496	total: 754ms	remaining: 19.3ms
975:	learn: 0.3342951	total: 755ms	remaining: 18.6ms
976:	learn: 0.3338885	total: 755ms	remaining: 17.8ms
977:	learn: 0.3334878	total: 756ms	remaining: 17ms
978:	learn: 0.3333744	total: 757ms	remaining: 16.2ms
979:	learn: 0.3328273	total: 758ms	remaining: 15.5ms
980:	learn: 0.3325875	total: 759ms	remaining: 14.7ms
981:	learn: 0.3321500	total: 759ms	remaining: 13.9ms
982:	learn: 0.3318978	total: 760ms	remaining: 13.1ms
983:	learn: 0.3314192	total: 761ms	remaining: 12.4ms
984:	learn: 0.3311618	total: 762ms	remaining: 11.6ms
985:	learn: 0.3309074	total: 763ms	remaining: 10.8ms
986:	learn: 0.3304707	total: 764ms	remaining: 10.1ms
987:	learn: 0.3303999	total: 765ms	remaining: 9.29ms
988:	learn: 0.3299260	total: 765ms	remaining: 8.51ms
989:	learn: 0.3295778	total: 766ms	remaining: 7.74ms
990:	learn: 0.3292826	total: 767ms	remaining: 6.96ms
991:	learn: 0.3289288	total: 768ms	remaining: 6.19ms
992:	learn: 0.3285139	total: 769ms	remaining: 5.42ms
993:	learn: 0.3279601	total: 770ms	remaining: 4.64ms
994:	learn: 0.3277501	total: 770ms	remaining: 3.87ms
995:	learn: 0.3275870	total: 771ms	remaining: 3.1ms
996:	learn: 0.3274331	total: 772ms	remaining: 2.32ms
997:	learn: 0.3272490	total: 773ms	remaining: 1.55ms
998:	learn: 0.3270320	total: 774ms	remaining: 774us
999:	learn: 0.3267704	total: 774ms	remaining: 0us

visulaize_performance_of_the_model(pred, y_test, modelname)

visualize_prediction_on_traindata(pred_cbr_trn,  y_train, modelname)

r2_score(y_test, pred)

0.6448669443472403

r2_score(y_train, pred_cbr_trn)

0.9523710155642153

Score is not improved... Again we have to check which record creating huge error.

data_check = df
data_check['Count of Failure'] = np.zeros(len(df))
for i in tqdm(range(3000)):
    x_train, x_test, y_train, y_test = train_test_split(df.drop(['LC50'], axis = 1), df['LC50'], test_size= 0.2)
    cbr = CatBoostRegressor(verbose=0).fit(x_train, y_train)
    for i in range(len(x_test)):
        pred = cbr.predict(x_test.iloc[i])
        error = abs(pred - y_test.iloc[i])
        if error >=1:
            find = data_check.loc[((data_check['CIC0'] == x_test.iloc[i][0]) & (data_check['SM1_Dz(Z)'] == x_test.iloc[i][1]) & (data_check['GATS1i'] == x_test.iloc[i][2]) & (data_check['NdsCH'] == x_test.iloc[i][3]) & (data_check['NdssC'] == x_test.iloc[i][4]) & (data_check['MLOGP'] == x_test.iloc[i][5]) )]
            count = find['Count of Failure']
            count += 1                      
            data_check.loc[( (data_check['CIC0'] == x_test.iloc[i][0]) &
                          (data_check['SM1_Dz(Z)'] == x_test.iloc[i][1]) &
                          (data_check['GATS1i'] == x_test.iloc[i][2]) &
                          (data_check['NdsCH'] == x_test.iloc[i][3]) &
                          (data_check['NdssC'] == x_test.iloc[i][4]) &
                          (data_check['MLOGP'] == x_test.iloc[i][5]) ), 'Count of Failure'] = count
        else:
            pass

100%|██████████| 3000/3000 [55:49<00:00,  1.12s/it] 

data_check.sort_values(by='Count of Failure', ascending=False, inplace=True)

len(data_check.loc[(data_check['Count of Failure'] > 0)])

273

len(data_check.loc[(data_check['Count of Failure'] == 0)])

418

df

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50	Count of Failure
402	2.841	0.880	1.705	0	3	0.226	1.647	648.0
179	2.031	0.872	1.475	0	1	0.202	6.424	644.0
551	1.094	1.236	1.461	0	1	0.996	1.911	633.0
197	3.739	0.000	1.250	1	2	3.267	2.149	629.0
33	3.833	0.405	1.522	0	1	3.492	2.092	627.0
...	...	...	...	...	...	...	...	...
273	3.900	0.429	1.572	0	1	2.297	3.842	0.0
272	2.800	0.693	1.091	0	1	1.437	3.603	0.0
268	2.591	0.331	1.629	0	0	0.874	2.395	0.0
266	1.279	1.327	1.284	0	0	2.200	4.697	0.0
345	1.822	0.681	0.794	0	0	2.335	3.696	0.0

691 rows × 8 columns

These 273 and 418 shows the error is huge in 273 records but in 418 records after 3000 train and test splits.

data_check.reset_index(drop=True, inplace=True)
data_check

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50	Count of Failure
0	2.841	0.880	1.705	0	3	0.226	1.647	648.0
1	2.031	0.872	1.475	0	1	0.202	6.424	644.0
2	1.094	1.236	1.461	0	1	0.996	1.911	633.0
3	3.739	0.000	1.250	1	2	3.267	2.149	629.0
4	3.833	0.405	1.522	0	1	3.492	2.092	627.0
...	...	...	...	...	...	...	...	...
686	3.900	0.429	1.572	0	1	2.297	3.842	0.0
687	2.800	0.693	1.091	0	1	1.437	3.603	0.0
688	2.591	0.331	1.629	0	0	0.874	2.395	0.0
689	1.279	1.327	1.284	0	0	2.200	4.697	0.0
690	1.822	0.681	0.794	0	0	2.335	3.696	0.0

691 rows × 8 columns

Approach 1: Let's split train and test data with an approach of 1st Eight records as train set and next 2 records as test set for every 10 records without changing the descending order of the data.

train_df, test_df = pd.DataFrame(), pd.DataFrame()
train_df_col1, train_df_col2, train_df_col3, train_df_col4, train_df_col5, train_df_col6, train_df_col7 =[],[],[],[],[],[],[]
test_df_col1, test_df_col2, test_df_col3, test_df_col4, test_df_col5, test_df_col6, test_df_col7 =[],[],[],[],[],[],[]
for i in tqdm(range(len(data_check))):
    if i == 0:
        train_df_col1.append(data_check.iloc[i][0])
        train_df_col2.append(data_check.iloc[i][1])
        train_df_col3.append(data_check.iloc[i][2])
        train_df_col4.append(data_check.iloc[i][3])
        train_df_col5.append(data_check.iloc[i][4])
        train_df_col6.append(data_check.iloc[i][5])
        train_df_col7.append(data_check.iloc[i][6]) 
        continue
    else:
        pass
  
    if (i % 9 == 0) or (i % 10 == 0):
        test_df_col1.append(data_check.iloc[i][0])
        test_df_col2.append(data_check.iloc[i][1])
        test_df_col3.append(data_check.iloc[i][2])
        test_df_col4.append(data_check.iloc[i][3])
        test_df_col5.append(data_check.iloc[i][4])
        test_df_col6.append(data_check.iloc[i][5])
        test_df_col7.append(data_check.iloc[i][6])
    else:
        train_df_col1.append(data_check.iloc[i][0])
        train_df_col2.append(data_check.iloc[i][1])
        train_df_col3.append(data_check.iloc[i][2])
        train_df_col4.append(data_check.iloc[i][3])
        train_df_col5.append(data_check.iloc[i][4])
        train_df_col6.append(data_check.iloc[i][5])
        train_df_col7.append(data_check.iloc[i][6])   
train_df['CIC0'], train_df['SM1_Dz(Z)'], train_df['GATS1i'] = train_df_col1, train_df_col2, train_df_col3
train_df['NdsCH'], train_df['NdssC'], train_df['MLOGP'], train_df['LC50'] = train_df_col4, train_df_col5, train_df_col6, train_df_col7

test_df['CIC0'], test_df['SM1_Dz(Z)'], test_df['GATS1i'] = test_df_col1, test_df_col2, test_df_col3
test_df['NdsCH'], test_df['NdssC'], test_df['MLOGP'], test_df['LC50'] = test_df_col4, test_df_col5, test_df_col6, test_df_col7

100%|██████████| 691/691 [00:00<00:00, 2567.39it/s]

train_df

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50
0	2.841	0.880	1.705	0.0	3.0	0.226	1.647
1	2.031	0.872	1.475	0.0	1.0	0.202	6.424
2	1.094	1.236	1.461	0.0	1.0	0.996	1.911
3	3.739	0.000	1.250	1.0	2.0	3.267	2.149
4	3.833	0.405	1.522	0.0	1.0	3.492	2.092
...	...	...	...	...	...	...	...
548	3.177	0.918	1.919	0.0	0.0	2.031	4.116
549	3.900	0.429	1.572	0.0	1.0	2.297	3.842
550	2.800	0.693	1.091	0.0	1.0	1.437	3.603
551	2.591	0.331	1.629	0.0	0.0	0.874	2.395
552	1.279	1.327	1.284	0.0	0.0	2.200	4.697

553 rows × 7 columns

test_df

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50
0	2.119	0.923	1.179	0.0	1.0	0.982	1.050
1	2.495	0.560	0.835	0.0	1.0	1.643	1.969
2	3.407	1.548	1.653	0.0	0.0	1.145	6.258
3	2.428	0.956	2.609	0.0	0.0	0.113	1.301
4	2.572	1.834	1.350	0.0	2.0	3.115	8.471
...	...	...	...	...	...	...	...
133	2.594	0.251	0.861	0.0	0.0	1.680	3.112
134	4.085	0.134	1.482	0.0	0.0	4.234	5.630
135	3.630	0.134	1.476	0.0	0.0	3.358	4.305
136	2.111	1.477	1.298	0.0	0.0	3.225	5.730
137	1.822	0.681	0.794	0.0	0.0	2.335	3.696

138 rows × 7 columns

x_train = train_df.drop(['LC50'], axis = 1)
x_test = test_df.drop(['LC50'], axis = 1)
y_train, y_test = train_df['LC50'], test_df['LC50']

cbr = CatBoostRegressor().fit(x_train, y_train)
pred = cbr.predict(x_test)
pred_cbr_trn = cbr.predict(x_train)
modelname = 'CatBoostRegressor Custom Data'
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred, y_test)

Learning rate set to 0.037285
0:	learn: 1.4992501	total: 930us	remaining: 930ms
1:	learn: 1.4738173	total: 1.67ms	remaining: 833ms
2:	learn: 1.4519159	total: 2.39ms	remaining: 794ms
3:	learn: 1.4282184	total: 3.14ms	remaining: 782ms
4:	learn: 1.4074069	total: 3.86ms	remaining: 769ms
5:	learn: 1.3858765	total: 4.58ms	remaining: 759ms
6:	learn: 1.3648956	total: 5.29ms	remaining: 751ms
7:	learn: 1.3455420	total: 6.03ms	remaining: 748ms
8:	learn: 1.3278063	total: 6.57ms	remaining: 723ms
9:	learn: 1.3098515	total: 7.3ms	remaining: 723ms
10:	learn: 1.2936774	total: 8.02ms	remaining: 721ms
11:	learn: 1.2777105	total: 8.75ms	remaining: 721ms
12:	learn: 1.2601647	total: 9.49ms	remaining: 720ms
13:	learn: 1.2450502	total: 10.2ms	remaining: 721ms
14:	learn: 1.2303358	total: 11ms	remaining: 722ms
15:	learn: 1.2153172	total: 11.7ms	remaining: 720ms
16:	learn: 1.2007379	total: 12.5ms	remaining: 720ms
17:	learn: 1.1879405	total: 13.2ms	remaining: 718ms
18:	learn: 1.1756805	total: 13.9ms	remaining: 718ms
19:	learn: 1.1642477	total: 14.7ms	remaining: 718ms
20:	learn: 1.1533488	total: 15.4ms	remaining: 719ms
21:	learn: 1.1427509	total: 16.1ms	remaining: 718ms
22:	learn: 1.1322080	total: 17ms	remaining: 722ms
23:	learn: 1.1215743	total: 17.8ms	remaining: 726ms
24:	learn: 1.1124890	total: 18.7ms	remaining: 727ms
25:	learn: 1.1030051	total: 19.5ms	remaining: 730ms
26:	learn: 1.0942995	total: 20.3ms	remaining: 733ms
27:	learn: 1.0858863	total: 21.2ms	remaining: 734ms
28:	learn: 1.0777452	total: 21.9ms	remaining: 735ms
29:	learn: 1.0690861	total: 22.7ms	remaining: 736ms
30:	learn: 1.0610474	total: 23.5ms	remaining: 736ms
31:	learn: 1.0551775	total: 24.4ms	remaining: 737ms
32:	learn: 1.0484685	total: 25.2ms	remaining: 739ms
33:	learn: 1.0408484	total: 26ms	remaining: 740ms
34:	learn: 1.0326628	total: 26.9ms	remaining: 742ms
35:	learn: 1.0266890	total: 27.7ms	remaining: 742ms
36:	learn: 1.0194904	total: 28.5ms	remaining: 742ms
37:	learn: 1.0137573	total: 29.4ms	remaining: 745ms
38:	learn: 1.0087202	total: 30.2ms	remaining: 744ms
39:	learn: 1.0030731	total: 31.1ms	remaining: 746ms
40:	learn: 0.9971357	total: 31.9ms	remaining: 746ms
41:	learn: 0.9917058	total: 32.7ms	remaining: 746ms
42:	learn: 0.9864484	total: 33.5ms	remaining: 746ms
43:	learn: 0.9815426	total: 34.3ms	remaining: 746ms
44:	learn: 0.9768469	total: 35.1ms	remaining: 746ms
45:	learn: 0.9720443	total: 35.9ms	remaining: 745ms
46:	learn: 0.9670647	total: 36.8ms	remaining: 746ms
47:	learn: 0.9618585	total: 37.5ms	remaining: 744ms
48:	learn: 0.9582010	total: 38.3ms	remaining: 744ms
49:	learn: 0.9540118	total: 39.1ms	remaining: 742ms
50:	learn: 0.9499237	total: 39.9ms	remaining: 742ms
51:	learn: 0.9453680	total: 40.6ms	remaining: 741ms
52:	learn: 0.9414172	total: 41.5ms	remaining: 742ms
53:	learn: 0.9374037	total: 42.2ms	remaining: 740ms
54:	learn: 0.9340794	total: 43ms	remaining: 739ms
55:	learn: 0.9302775	total: 43.8ms	remaining: 739ms
56:	learn: 0.9267049	total: 44.7ms	remaining: 739ms
57:	learn: 0.9227261	total: 45.5ms	remaining: 738ms
58:	learn: 0.9201264	total: 46.2ms	remaining: 737ms
59:	learn: 0.9169558	total: 47ms	remaining: 737ms
60:	learn: 0.9142339	total: 47.8ms	remaining: 736ms
61:	learn: 0.9104640	total: 48.6ms	remaining: 735ms
62:	learn: 0.9071347	total: 49.4ms	remaining: 735ms
63:	learn: 0.9034183	total: 50.1ms	remaining: 733ms
64:	learn: 0.9005758	total: 50.9ms	remaining: 732ms
65:	learn: 0.8972617	total: 51.8ms	remaining: 732ms
66:	learn: 0.8947228	total: 52.5ms	remaining: 731ms
67:	learn: 0.8912124	total: 53.3ms	remaining: 731ms
68:	learn: 0.8883977	total: 54.1ms	remaining: 729ms
69:	learn: 0.8856666	total: 54.8ms	remaining: 728ms
70:	learn: 0.8834959	total: 55.6ms	remaining: 727ms
71:	learn: 0.8801970	total: 56.4ms	remaining: 727ms
72:	learn: 0.8782662	total: 57.1ms	remaining: 726ms
73:	learn: 0.8765204	total: 57.7ms	remaining: 723ms
74:	learn: 0.8744176	total: 58.5ms	remaining: 721ms
75:	learn: 0.8717128	total: 59.3ms	remaining: 721ms
76:	learn: 0.8688579	total: 60.2ms	remaining: 721ms
77:	learn: 0.8660996	total: 61.1ms	remaining: 722ms
78:	learn: 0.8640556	total: 62.1ms	remaining: 723ms
79:	learn: 0.8618195	total: 62.8ms	remaining: 723ms
80:	learn: 0.8591201	total: 63.7ms	remaining: 723ms
81:	learn: 0.8566769	total: 64.5ms	remaining: 722ms
82:	learn: 0.8555328	total: 65.4ms	remaining: 723ms
83:	learn: 0.8536620	total: 66.4ms	remaining: 724ms
84:	learn: 0.8521233	total: 67.3ms	remaining: 724ms
85:	learn: 0.8501093	total: 68.1ms	remaining: 724ms
86:	learn: 0.8489519	total: 69ms	remaining: 724ms
87:	learn: 0.8477132	total: 69.5ms	remaining: 720ms
88:	learn: 0.8451275	total: 70.3ms	remaining: 720ms
89:	learn: 0.8438999	total: 71.1ms	remaining: 719ms
90:	learn: 0.8422974	total: 71.9ms	remaining: 718ms
91:	learn: 0.8407357	total: 72.7ms	remaining: 717ms
92:	learn: 0.8397619	total: 73.6ms	remaining: 717ms
93:	learn: 0.8376113	total: 74.3ms	remaining: 716ms
94:	learn: 0.8364830	total: 75.1ms	remaining: 716ms
95:	learn: 0.8343451	total: 75.9ms	remaining: 715ms
96:	learn: 0.8325836	total: 76.7ms	remaining: 714ms
97:	learn: 0.8313572	total: 77.6ms	remaining: 714ms
98:	learn: 0.8300834	total: 78.3ms	remaining: 713ms
99:	learn: 0.8283257	total: 79.1ms	remaining: 712ms
100:	learn: 0.8273159	total: 79.9ms	remaining: 711ms
101:	learn: 0.8256819	total: 80.6ms	remaining: 710ms
102:	learn: 0.8242807	total: 81.3ms	remaining: 708ms
103:	learn: 0.8236540	total: 81.7ms	remaining: 704ms
104:	learn: 0.8228731	total: 82.5ms	remaining: 703ms
105:	learn: 0.8214231	total: 83.2ms	remaining: 702ms
106:	learn: 0.8211468	total: 83.9ms	remaining: 700ms
107:	learn: 0.8196265	total: 84.6ms	remaining: 699ms
108:	learn: 0.8189066	total: 85.3ms	remaining: 698ms
109:	learn: 0.8164712	total: 86.2ms	remaining: 697ms
110:	learn: 0.8150725	total: 86.9ms	remaining: 696ms
111:	learn: 0.8132651	total: 87.6ms	remaining: 695ms
112:	learn: 0.8113880	total: 88.3ms	remaining: 693ms
113:	learn: 0.8106421	total: 89.1ms	remaining: 692ms
114:	learn: 0.8093368	total: 89.8ms	remaining: 691ms
115:	learn: 0.8085334	total: 90.5ms	remaining: 690ms
116:	learn: 0.8069238	total: 91.2ms	remaining: 689ms
117:	learn: 0.8055251	total: 92ms	remaining: 687ms
118:	learn: 0.8046944	total: 92.7ms	remaining: 686ms
119:	learn: 0.8046443	total: 92.9ms	remaining: 682ms
120:	learn: 0.8034098	total: 93.7ms	remaining: 680ms
121:	learn: 0.8019204	total: 94.4ms	remaining: 679ms
122:	learn: 0.8004356	total: 95.1ms	remaining: 678ms
123:	learn: 0.7996843	total: 95.8ms	remaining: 677ms
124:	learn: 0.7985674	total: 96.5ms	remaining: 676ms
125:	learn: 0.7974158	total: 97.3ms	remaining: 675ms
126:	learn: 0.7960538	total: 98ms	remaining: 674ms
127:	learn: 0.7947978	total: 98.7ms	remaining: 673ms
128:	learn: 0.7924597	total: 99.5ms	remaining: 672ms
129:	learn: 0.7912523	total: 100ms	remaining: 671ms
130:	learn: 0.7894850	total: 101ms	remaining: 669ms
131:	learn: 0.7889372	total: 102ms	remaining: 668ms
132:	learn: 0.7876402	total: 102ms	remaining: 668ms
133:	learn: 0.7857075	total: 103ms	remaining: 667ms
134:	learn: 0.7847858	total: 104ms	remaining: 666ms
135:	learn: 0.7837261	total: 105ms	remaining: 665ms
136:	learn: 0.7829850	total: 105ms	remaining: 664ms
137:	learn: 0.7813881	total: 106ms	remaining: 663ms
138:	learn: 0.7795047	total: 107ms	remaining: 662ms
139:	learn: 0.7783805	total: 108ms	remaining: 661ms
140:	learn: 0.7778816	total: 108ms	remaining: 660ms
141:	learn: 0.7761484	total: 109ms	remaining: 659ms
142:	learn: 0.7750975	total: 110ms	remaining: 658ms
143:	learn: 0.7738356	total: 110ms	remaining: 656ms
144:	learn: 0.7728872	total: 111ms	remaining: 655ms
145:	learn: 0.7713438	total: 112ms	remaining: 654ms
146:	learn: 0.7704501	total: 113ms	remaining: 653ms
147:	learn: 0.7688132	total: 113ms	remaining: 652ms
148:	learn: 0.7674799	total: 114ms	remaining: 651ms
149:	learn: 0.7664838	total: 115ms	remaining: 650ms
150:	learn: 0.7652216	total: 115ms	remaining: 649ms
151:	learn: 0.7648545	total: 116ms	remaining: 648ms
152:	learn: 0.7640382	total: 117ms	remaining: 647ms
153:	learn: 0.7632625	total: 118ms	remaining: 646ms
154:	learn: 0.7618851	total: 118ms	remaining: 645ms
155:	learn: 0.7607320	total: 119ms	remaining: 644ms
156:	learn: 0.7596071	total: 120ms	remaining: 643ms
157:	learn: 0.7590895	total: 121ms	remaining: 642ms
158:	learn: 0.7580369	total: 121ms	remaining: 641ms
159:	learn: 0.7568069	total: 122ms	remaining: 640ms
160:	learn: 0.7553453	total: 123ms	remaining: 639ms
161:	learn: 0.7541769	total: 123ms	remaining: 639ms
162:	learn: 0.7527556	total: 124ms	remaining: 638ms
163:	learn: 0.7517221	total: 125ms	remaining: 637ms
164:	learn: 0.7505250	total: 126ms	remaining: 636ms
165:	learn: 0.7492067	total: 126ms	remaining: 635ms
166:	learn: 0.7481732	total: 127ms	remaining: 634ms
167:	learn: 0.7473690	total: 128ms	remaining: 633ms
168:	learn: 0.7463908	total: 129ms	remaining: 632ms
169:	learn: 0.7453944	total: 129ms	remaining: 631ms
170:	learn: 0.7444196	total: 130ms	remaining: 630ms
171:	learn: 0.7433759	total: 131ms	remaining: 629ms
172:	learn: 0.7425080	total: 131ms	remaining: 628ms
173:	learn: 0.7415419	total: 132ms	remaining: 627ms
174:	learn: 0.7407770	total: 133ms	remaining: 626ms
175:	learn: 0.7391562	total: 134ms	remaining: 626ms
176:	learn: 0.7378298	total: 134ms	remaining: 625ms
177:	learn: 0.7370858	total: 135ms	remaining: 624ms
178:	learn: 0.7355919	total: 136ms	remaining: 623ms
179:	learn: 0.7347316	total: 137ms	remaining: 622ms
180:	learn: 0.7342793	total: 137ms	remaining: 621ms
181:	learn: 0.7339215	total: 138ms	remaining: 620ms
182:	learn: 0.7329258	total: 139ms	remaining: 619ms
183:	learn: 0.7318132	total: 139ms	remaining: 619ms
184:	learn: 0.7313059	total: 140ms	remaining: 618ms
185:	learn: 0.7300020	total: 141ms	remaining: 617ms
186:	learn: 0.7294029	total: 142ms	remaining: 616ms
187:	learn: 0.7282089	total: 142ms	remaining: 615ms
188:	learn: 0.7272999	total: 143ms	remaining: 614ms
189:	learn: 0.7264016	total: 144ms	remaining: 613ms
190:	learn: 0.7254068	total: 144ms	remaining: 612ms
191:	learn: 0.7243673	total: 145ms	remaining: 611ms
192:	learn: 0.7239736	total: 146ms	remaining: 610ms
193:	learn: 0.7232526	total: 147ms	remaining: 610ms
194:	learn: 0.7215579	total: 147ms	remaining: 609ms
195:	learn: 0.7203975	total: 148ms	remaining: 608ms
196:	learn: 0.7196174	total: 149ms	remaining: 607ms
197:	learn: 0.7188425	total: 150ms	remaining: 606ms
198:	learn: 0.7182330	total: 150ms	remaining: 605ms
199:	learn: 0.7171308	total: 151ms	remaining: 604ms
200:	learn: 0.7162142	total: 152ms	remaining: 604ms
201:	learn: 0.7155881	total: 153ms	remaining: 603ms
202:	learn: 0.7140747	total: 153ms	remaining: 602ms
203:	learn: 0.7133175	total: 154ms	remaining: 601ms
204:	learn: 0.7127983	total: 155ms	remaining: 600ms
205:	learn: 0.7121278	total: 155ms	remaining: 599ms
206:	learn: 0.7112959	total: 156ms	remaining: 598ms
207:	learn: 0.7099120	total: 157ms	remaining: 598ms
208:	learn: 0.7089708	total: 158ms	remaining: 597ms
209:	learn: 0.7083179	total: 158ms	remaining: 596ms
210:	learn: 0.7078879	total: 159ms	remaining: 595ms
211:	learn: 0.7069993	total: 160ms	remaining: 595ms
212:	learn: 0.7058248	total: 161ms	remaining: 594ms
213:	learn: 0.7039841	total: 161ms	remaining: 593ms
214:	learn: 0.7028142	total: 162ms	remaining: 592ms
215:	learn: 0.7022536	total: 163ms	remaining: 591ms
216:	learn: 0.7010576	total: 164ms	remaining: 590ms
217:	learn: 0.7005527	total: 164ms	remaining: 589ms
218:	learn: 0.6999383	total: 165ms	remaining: 589ms
219:	learn: 0.6994915	total: 166ms	remaining: 588ms
220:	learn: 0.6982709	total: 166ms	remaining: 587ms
221:	learn: 0.6975539	total: 167ms	remaining: 586ms
222:	learn: 0.6968384	total: 168ms	remaining: 585ms
223:	learn: 0.6965677	total: 169ms	remaining: 584ms
224:	learn: 0.6956372	total: 169ms	remaining: 583ms
225:	learn: 0.6951531	total: 170ms	remaining: 582ms
226:	learn: 0.6942906	total: 171ms	remaining: 582ms
227:	learn: 0.6938584	total: 172ms	remaining: 581ms
228:	learn: 0.6924346	total: 172ms	remaining: 580ms
229:	learn: 0.6916827	total: 173ms	remaining: 579ms
230:	learn: 0.6911242	total: 174ms	remaining: 578ms
231:	learn: 0.6896246	total: 174ms	remaining: 578ms
232:	learn: 0.6882539	total: 175ms	remaining: 577ms
233:	learn: 0.6879413	total: 176ms	remaining: 576ms
234:	learn: 0.6874409	total: 177ms	remaining: 575ms
235:	learn: 0.6869571	total: 177ms	remaining: 575ms
236:	learn: 0.6860517	total: 178ms	remaining: 574ms
237:	learn: 0.6850852	total: 179ms	remaining: 573ms
238:	learn: 0.6847530	total: 180ms	remaining: 572ms
239:	learn: 0.6843268	total: 180ms	remaining: 571ms
240:	learn: 0.6835486	total: 181ms	remaining: 570ms
241:	learn: 0.6831398	total: 182ms	remaining: 570ms
242:	learn: 0.6828520	total: 183ms	remaining: 569ms
243:	learn: 0.6824519	total: 183ms	remaining: 568ms
244:	learn: 0.6820243	total: 184ms	remaining: 567ms
245:	learn: 0.6810828	total: 185ms	remaining: 567ms
246:	learn: 0.6801029	total: 186ms	remaining: 566ms
247:	learn: 0.6798310	total: 186ms	remaining: 565ms
248:	learn: 0.6788666	total: 187ms	remaining: 564ms
249:	learn: 0.6785073	total: 188ms	remaining: 563ms
250:	learn: 0.6777158	total: 189ms	remaining: 564ms
251:	learn: 0.6768411	total: 190ms	remaining: 564ms
252:	learn: 0.6765850	total: 191ms	remaining: 563ms
253:	learn: 0.6762374	total: 192ms	remaining: 563ms
254:	learn: 0.6759011	total: 192ms	remaining: 562ms
255:	learn: 0.6750739	total: 193ms	remaining: 561ms
256:	learn: 0.6741528	total: 194ms	remaining: 560ms
257:	learn: 0.6727505	total: 195ms	remaining: 560ms
258:	learn: 0.6721998	total: 195ms	remaining: 559ms
259:	learn: 0.6710139	total: 196ms	remaining: 558ms
260:	learn: 0.6702288	total: 197ms	remaining: 557ms
261:	learn: 0.6698149	total: 198ms	remaining: 556ms
262:	learn: 0.6687839	total: 198ms	remaining: 556ms
263:	learn: 0.6675117	total: 199ms	remaining: 555ms
264:	learn: 0.6665330	total: 200ms	remaining: 554ms
265:	learn: 0.6657891	total: 201ms	remaining: 553ms
266:	learn: 0.6653921	total: 201ms	remaining: 553ms
267:	learn: 0.6644795	total: 202ms	remaining: 552ms
268:	learn: 0.6641377	total: 203ms	remaining: 551ms
269:	learn: 0.6638391	total: 204ms	remaining: 551ms
270:	learn: 0.6634663	total: 205ms	remaining: 550ms
271:	learn: 0.6631749	total: 205ms	remaining: 550ms
272:	learn: 0.6619751	total: 206ms	remaining: 549ms
273:	learn: 0.6613207	total: 207ms	remaining: 548ms
274:	learn: 0.6611006	total: 208ms	remaining: 548ms
275:	learn: 0.6598283	total: 208ms	remaining: 547ms
276:	learn: 0.6585129	total: 209ms	remaining: 546ms
277:	learn: 0.6575314	total: 210ms	remaining: 545ms
278:	learn: 0.6563350	total: 211ms	remaining: 545ms
279:	learn: 0.6557867	total: 212ms	remaining: 544ms
280:	learn: 0.6550198	total: 212ms	remaining: 544ms
281:	learn: 0.6540170	total: 213ms	remaining: 543ms
282:	learn: 0.6529948	total: 214ms	remaining: 543ms
283:	learn: 0.6527444	total: 215ms	remaining: 542ms
284:	learn: 0.6518184	total: 216ms	remaining: 541ms
285:	learn: 0.6514756	total: 217ms	remaining: 541ms
286:	learn: 0.6512742	total: 217ms	remaining: 540ms
287:	learn: 0.6503231	total: 218ms	remaining: 539ms
288:	learn: 0.6495749	total: 219ms	remaining: 539ms
289:	learn: 0.6489409	total: 220ms	remaining: 538ms
290:	learn: 0.6486321	total: 221ms	remaining: 537ms
291:	learn: 0.6479892	total: 221ms	remaining: 537ms
292:	learn: 0.6470216	total: 222ms	remaining: 536ms
293:	learn: 0.6467585	total: 223ms	remaining: 535ms
294:	learn: 0.6465671	total: 224ms	remaining: 535ms
295:	learn: 0.6458025	total: 224ms	remaining: 534ms
296:	learn: 0.6451176	total: 225ms	remaining: 533ms
297:	learn: 0.6442983	total: 226ms	remaining: 533ms
298:	learn: 0.6437376	total: 227ms	remaining: 532ms
299:	learn: 0.6431404	total: 228ms	remaining: 531ms
300:	learn: 0.6424670	total: 229ms	remaining: 531ms
301:	learn: 0.6417509	total: 229ms	remaining: 530ms
302:	learn: 0.6410611	total: 230ms	remaining: 529ms
303:	learn: 0.6407646	total: 231ms	remaining: 528ms
304:	learn: 0.6397490	total: 232ms	remaining: 528ms
305:	learn: 0.6389931	total: 233ms	remaining: 527ms
306:	learn: 0.6385497	total: 233ms	remaining: 527ms
307:	learn: 0.6376900	total: 234ms	remaining: 526ms
308:	learn: 0.6370215	total: 235ms	remaining: 526ms
309:	learn: 0.6362710	total: 236ms	remaining: 525ms
310:	learn: 0.6352018	total: 237ms	remaining: 524ms
311:	learn: 0.6343042	total: 237ms	remaining: 524ms
312:	learn: 0.6340649	total: 238ms	remaining: 523ms
313:	learn: 0.6333316	total: 239ms	remaining: 522ms
314:	learn: 0.6331490	total: 240ms	remaining: 522ms
315:	learn: 0.6326105	total: 241ms	remaining: 521ms
316:	learn: 0.6313336	total: 241ms	remaining: 520ms
317:	learn: 0.6301635	total: 242ms	remaining: 519ms
318:	learn: 0.6291089	total: 243ms	remaining: 519ms
319:	learn: 0.6284029	total: 244ms	remaining: 518ms
320:	learn: 0.6277633	total: 244ms	remaining: 517ms
321:	learn: 0.6274479	total: 245ms	remaining: 516ms
322:	learn: 0.6271250	total: 246ms	remaining: 515ms
323:	learn: 0.6266248	total: 247ms	remaining: 515ms
324:	learn: 0.6256436	total: 248ms	remaining: 514ms
325:	learn: 0.6251562	total: 248ms	remaining: 513ms
326:	learn: 0.6238657	total: 249ms	remaining: 512ms
327:	learn: 0.6228880	total: 250ms	remaining: 512ms
328:	learn: 0.6222475	total: 251ms	remaining: 511ms
329:	learn: 0.6217630	total: 251ms	remaining: 510ms
330:	learn: 0.6210267	total: 252ms	remaining: 509ms
331:	learn: 0.6199219	total: 253ms	remaining: 508ms
332:	learn: 0.6188823	total: 253ms	remaining: 508ms
333:	learn: 0.6179338	total: 254ms	remaining: 507ms
334:	learn: 0.6173658	total: 255ms	remaining: 506ms
335:	learn: 0.6167140	total: 256ms	remaining: 505ms
336:	learn: 0.6161235	total: 256ms	remaining: 504ms
337:	learn: 0.6154102	total: 257ms	remaining: 504ms
338:	learn: 0.6150206	total: 258ms	remaining: 503ms
339:	learn: 0.6139165	total: 259ms	remaining: 502ms
340:	learn: 0.6132110	total: 259ms	remaining: 501ms
341:	learn: 0.6122876	total: 260ms	remaining: 500ms
342:	learn: 0.6115983	total: 261ms	remaining: 500ms
343:	learn: 0.6112625	total: 262ms	remaining: 499ms
344:	learn: 0.6110673	total: 262ms	remaining: 498ms
345:	learn: 0.6105257	total: 263ms	remaining: 497ms
346:	learn: 0.6098328	total: 264ms	remaining: 497ms
347:	learn: 0.6085638	total: 265ms	remaining: 496ms
348:	learn: 0.6083732	total: 265ms	remaining: 495ms
349:	learn: 0.6074973	total: 266ms	remaining: 494ms
350:	learn: 0.6073304	total: 267ms	remaining: 493ms
351:	learn: 0.6064986	total: 268ms	remaining: 493ms
352:	learn: 0.6060490	total: 268ms	remaining: 492ms
353:	learn: 0.6054220	total: 269ms	remaining: 491ms
354:	learn: 0.6046687	total: 270ms	remaining: 490ms
355:	learn: 0.6041575	total: 270ms	remaining: 489ms
356:	learn: 0.6032175	total: 271ms	remaining: 489ms
357:	learn: 0.6022975	total: 272ms	remaining: 488ms
358:	learn: 0.6014567	total: 273ms	remaining: 487ms
359:	learn: 0.6007572	total: 273ms	remaining: 486ms
360:	learn: 0.5998936	total: 274ms	remaining: 485ms
361:	learn: 0.5994062	total: 275ms	remaining: 485ms
362:	learn: 0.5988554	total: 276ms	remaining: 484ms
363:	learn: 0.5976230	total: 277ms	remaining: 483ms
364:	learn: 0.5971841	total: 277ms	remaining: 483ms
365:	learn: 0.5970364	total: 278ms	remaining: 482ms
366:	learn: 0.5964123	total: 279ms	remaining: 481ms
367:	learn: 0.5953634	total: 280ms	remaining: 480ms
368:	learn: 0.5946295	total: 280ms	remaining: 479ms
369:	learn: 0.5944985	total: 281ms	remaining: 479ms
370:	learn: 0.5935432	total: 282ms	remaining: 478ms
371:	learn: 0.5920588	total: 283ms	remaining: 477ms
372:	learn: 0.5915994	total: 283ms	remaining: 476ms
373:	learn: 0.5911582	total: 284ms	remaining: 475ms
374:	learn: 0.5903802	total: 285ms	remaining: 475ms
375:	learn: 0.5895429	total: 286ms	remaining: 474ms
376:	learn: 0.5886876	total: 286ms	remaining: 473ms
377:	learn: 0.5883568	total: 287ms	remaining: 472ms
378:	learn: 0.5876212	total: 288ms	remaining: 471ms
379:	learn: 0.5865669	total: 288ms	remaining: 471ms
380:	learn: 0.5857786	total: 289ms	remaining: 470ms
381:	learn: 0.5849741	total: 290ms	remaining: 469ms
382:	learn: 0.5842858	total: 291ms	remaining: 468ms
383:	learn: 0.5833741	total: 291ms	remaining: 467ms
384:	learn: 0.5827357	total: 292ms	remaining: 467ms
385:	learn: 0.5816199	total: 293ms	remaining: 466ms
386:	learn: 0.5808773	total: 294ms	remaining: 465ms
387:	learn: 0.5803995	total: 294ms	remaining: 464ms
388:	learn: 0.5794072	total: 295ms	remaining: 464ms
389:	learn: 0.5784324	total: 296ms	remaining: 463ms
390:	learn: 0.5777407	total: 297ms	remaining: 462ms
391:	learn: 0.5771514	total: 297ms	remaining: 461ms
392:	learn: 0.5769029	total: 298ms	remaining: 460ms
393:	learn: 0.5767398	total: 299ms	remaining: 459ms
394:	learn: 0.5760201	total: 299ms	remaining: 459ms
395:	learn: 0.5755368	total: 300ms	remaining: 458ms
396:	learn: 0.5755045	total: 301ms	remaining: 457ms
397:	learn: 0.5749185	total: 302ms	remaining: 456ms
398:	learn: 0.5738501	total: 302ms	remaining: 455ms
399:	learn: 0.5725572	total: 303ms	remaining: 455ms
400:	learn: 0.5718988	total: 304ms	remaining: 454ms
401:	learn: 0.5713314	total: 305ms	remaining: 453ms
402:	learn: 0.5705605	total: 305ms	remaining: 452ms
403:	learn: 0.5691395	total: 306ms	remaining: 452ms
404:	learn: 0.5678704	total: 307ms	remaining: 451ms
405:	learn: 0.5670486	total: 308ms	remaining: 450ms
406:	learn: 0.5660535	total: 308ms	remaining: 449ms
407:	learn: 0.5653731	total: 309ms	remaining: 448ms
408:	learn: 0.5647352	total: 310ms	remaining: 448ms
409:	learn: 0.5641733	total: 310ms	remaining: 447ms
410:	learn: 0.5630231	total: 311ms	remaining: 446ms
411:	learn: 0.5624205	total: 312ms	remaining: 445ms
412:	learn: 0.5620259	total: 313ms	remaining: 444ms
413:	learn: 0.5616368	total: 313ms	remaining: 444ms
414:	learn: 0.5614695	total: 314ms	remaining: 443ms
415:	learn: 0.5604359	total: 315ms	remaining: 442ms
416:	learn: 0.5603376	total: 316ms	remaining: 441ms
417:	learn: 0.5590437	total: 316ms	remaining: 441ms
418:	learn: 0.5584578	total: 317ms	remaining: 440ms
419:	learn: 0.5580397	total: 318ms	remaining: 439ms
420:	learn: 0.5567331	total: 319ms	remaining: 438ms
421:	learn: 0.5557528	total: 319ms	remaining: 437ms
422:	learn: 0.5547919	total: 320ms	remaining: 437ms
423:	learn: 0.5544206	total: 321ms	remaining: 436ms
424:	learn: 0.5538794	total: 322ms	remaining: 435ms
425:	learn: 0.5532185	total: 322ms	remaining: 434ms
426:	learn: 0.5529621	total: 323ms	remaining: 433ms
427:	learn: 0.5524284	total: 324ms	remaining: 433ms
428:	learn: 0.5514786	total: 324ms	remaining: 432ms
429:	learn: 0.5508944	total: 325ms	remaining: 431ms
430:	learn: 0.5496263	total: 326ms	remaining: 430ms
431:	learn: 0.5489015	total: 327ms	remaining: 430ms
432:	learn: 0.5486335	total: 327ms	remaining: 429ms
433:	learn: 0.5479318	total: 328ms	remaining: 428ms
434:	learn: 0.5472232	total: 329ms	remaining: 427ms
435:	learn: 0.5460390	total: 330ms	remaining: 426ms
436:	learn: 0.5449055	total: 330ms	remaining: 426ms
437:	learn: 0.5440536	total: 331ms	remaining: 425ms
438:	learn: 0.5433652	total: 332ms	remaining: 424ms
439:	learn: 0.5427428	total: 333ms	remaining: 423ms
440:	learn: 0.5421420	total: 333ms	remaining: 422ms
441:	learn: 0.5416949	total: 334ms	remaining: 422ms
442:	learn: 0.5415054	total: 335ms	remaining: 421ms
443:	learn: 0.5411990	total: 336ms	remaining: 420ms
444:	learn: 0.5411089	total: 336ms	remaining: 419ms
445:	learn: 0.5404722	total: 337ms	remaining: 419ms
446:	learn: 0.5398553	total: 338ms	remaining: 418ms
447:	learn: 0.5397610	total: 338ms	remaining: 417ms
448:	learn: 0.5393486	total: 339ms	remaining: 416ms
449:	learn: 0.5385603	total: 340ms	remaining: 415ms
450:	learn: 0.5380298	total: 341ms	remaining: 415ms
451:	learn: 0.5371593	total: 341ms	remaining: 414ms
452:	learn: 0.5363314	total: 342ms	remaining: 413ms
453:	learn: 0.5362407	total: 343ms	remaining: 412ms
454:	learn: 0.5358541	total: 344ms	remaining: 412ms
455:	learn: 0.5348928	total: 344ms	remaining: 411ms
456:	learn: 0.5341391	total: 345ms	remaining: 410ms
457:	learn: 0.5335357	total: 346ms	remaining: 409ms
458:	learn: 0.5325093	total: 347ms	remaining: 408ms
459:	learn: 0.5314510	total: 347ms	remaining: 408ms
460:	learn: 0.5309870	total: 348ms	remaining: 407ms
461:	learn: 0.5302058	total: 349ms	remaining: 406ms
462:	learn: 0.5298841	total: 350ms	remaining: 406ms
463:	learn: 0.5296284	total: 350ms	remaining: 405ms
464:	learn: 0.5289426	total: 351ms	remaining: 404ms
465:	learn: 0.5281968	total: 352ms	remaining: 403ms
466:	learn: 0.5278687	total: 353ms	remaining: 403ms
467:	learn: 0.5274323	total: 354ms	remaining: 402ms
468:	learn: 0.5264005	total: 355ms	remaining: 402ms
469:	learn: 0.5262997	total: 356ms	remaining: 401ms
470:	learn: 0.5262291	total: 356ms	remaining: 400ms
471:	learn: 0.5256698	total: 357ms	remaining: 400ms
472:	learn: 0.5256316	total: 358ms	remaining: 399ms
473:	learn: 0.5251375	total: 359ms	remaining: 398ms
474:	learn: 0.5245763	total: 360ms	remaining: 397ms
475:	learn: 0.5239912	total: 360ms	remaining: 397ms
476:	learn: 0.5235293	total: 361ms	remaining: 396ms
477:	learn: 0.5232841	total: 362ms	remaining: 395ms
478:	learn: 0.5229658	total: 363ms	remaining: 395ms
479:	learn: 0.5226048	total: 364ms	remaining: 394ms
480:	learn: 0.5221334	total: 365ms	remaining: 393ms
481:	learn: 0.5216109	total: 365ms	remaining: 393ms
482:	learn: 0.5212378	total: 366ms	remaining: 392ms
483:	learn: 0.5209853	total: 367ms	remaining: 391ms
484:	learn: 0.5198441	total: 368ms	remaining: 390ms
485:	learn: 0.5187166	total: 369ms	remaining: 390ms
486:	learn: 0.5183665	total: 369ms	remaining: 389ms
487:	learn: 0.5180951	total: 370ms	remaining: 388ms
488:	learn: 0.5173052	total: 371ms	remaining: 388ms
489:	learn: 0.5166552	total: 372ms	remaining: 387ms
490:	learn: 0.5165618	total: 372ms	remaining: 386ms
491:	learn: 0.5156978	total: 373ms	remaining: 385ms
492:	learn: 0.5154103	total: 374ms	remaining: 385ms
493:	learn: 0.5153303	total: 375ms	remaining: 384ms
494:	learn: 0.5147624	total: 376ms	remaining: 383ms
495:	learn: 0.5144142	total: 377ms	remaining: 383ms
496:	learn: 0.5139445	total: 377ms	remaining: 382ms
497:	learn: 0.5131062	total: 378ms	remaining: 381ms
498:	learn: 0.5128067	total: 379ms	remaining: 380ms
499:	learn: 0.5126924	total: 380ms	remaining: 380ms
500:	learn: 0.5125489	total: 380ms	remaining: 379ms
501:	learn: 0.5122935	total: 381ms	remaining: 378ms
502:	learn: 0.5115892	total: 382ms	remaining: 377ms
503:	learn: 0.5113846	total: 383ms	remaining: 377ms
504:	learn: 0.5112931	total: 383ms	remaining: 376ms
505:	learn: 0.5108592	total: 384ms	remaining: 375ms
506:	learn: 0.5104112	total: 385ms	remaining: 374ms
507:	learn: 0.5092039	total: 386ms	remaining: 374ms
508:	learn: 0.5085623	total: 386ms	remaining: 373ms
509:	learn: 0.5077673	total: 387ms	remaining: 372ms
510:	learn: 0.5073033	total: 388ms	remaining: 371ms
511:	learn: 0.5070449	total: 389ms	remaining: 370ms
512:	learn: 0.5064175	total: 389ms	remaining: 370ms
513:	learn: 0.5063101	total: 390ms	remaining: 369ms
514:	learn: 0.5054561	total: 391ms	remaining: 368ms
515:	learn: 0.5047466	total: 392ms	remaining: 367ms
516:	learn: 0.5039248	total: 392ms	remaining: 367ms
517:	learn: 0.5030447	total: 393ms	remaining: 366ms
518:	learn: 0.5025132	total: 394ms	remaining: 365ms
519:	learn: 0.5015502	total: 395ms	remaining: 364ms
520:	learn: 0.5005880	total: 396ms	remaining: 364ms
521:	learn: 0.5000690	total: 396ms	remaining: 363ms
522:	learn: 0.4994020	total: 397ms	remaining: 362ms
523:	learn: 0.4989052	total: 398ms	remaining: 361ms
524:	learn: 0.4986798	total: 398ms	remaining: 361ms
525:	learn: 0.4978019	total: 399ms	remaining: 360ms
526:	learn: 0.4973143	total: 400ms	remaining: 359ms
527:	learn: 0.4967975	total: 401ms	remaining: 358ms
528:	learn: 0.4963851	total: 401ms	remaining: 357ms
529:	learn: 0.4959227	total: 402ms	remaining: 357ms
530:	learn: 0.4951463	total: 403ms	remaining: 356ms
531:	learn: 0.4950621	total: 404ms	remaining: 355ms
532:	learn: 0.4944553	total: 404ms	remaining: 354ms
533:	learn: 0.4943660	total: 405ms	remaining: 354ms
534:	learn: 0.4936110	total: 406ms	remaining: 353ms
535:	learn: 0.4932807	total: 407ms	remaining: 352ms
536:	learn: 0.4925067	total: 407ms	remaining: 351ms
537:	learn: 0.4917657	total: 408ms	remaining: 350ms
538:	learn: 0.4908763	total: 409ms	remaining: 350ms
539:	learn: 0.4896701	total: 410ms	remaining: 349ms
540:	learn: 0.4886531	total: 410ms	remaining: 348ms
541:	learn: 0.4873816	total: 411ms	remaining: 347ms
542:	learn: 0.4865789	total: 412ms	remaining: 347ms
543:	learn: 0.4861297	total: 413ms	remaining: 346ms
544:	learn: 0.4852550	total: 413ms	remaining: 345ms
545:	learn: 0.4846827	total: 414ms	remaining: 344ms
546:	learn: 0.4841367	total: 415ms	remaining: 344ms
547:	learn: 0.4836761	total: 416ms	remaining: 343ms
548:	learn: 0.4833186	total: 416ms	remaining: 342ms
549:	learn: 0.4830439	total: 417ms	remaining: 341ms
550:	learn: 0.4826393	total: 418ms	remaining: 341ms
551:	learn: 0.4820762	total: 419ms	remaining: 340ms
552:	learn: 0.4817746	total: 419ms	remaining: 339ms
553:	learn: 0.4815718	total: 420ms	remaining: 338ms
554:	learn: 0.4808591	total: 421ms	remaining: 337ms
555:	learn: 0.4807879	total: 422ms	remaining: 337ms
556:	learn: 0.4807180	total: 422ms	remaining: 336ms
557:	learn: 0.4801245	total: 423ms	remaining: 335ms
558:	learn: 0.4796469	total: 424ms	remaining: 334ms
559:	learn: 0.4788414	total: 425ms	remaining: 334ms
560:	learn: 0.4783643	total: 426ms	remaining: 333ms
561:	learn: 0.4779090	total: 426ms	remaining: 332ms
562:	learn: 0.4773272	total: 427ms	remaining: 332ms
563:	learn: 0.4772596	total: 428ms	remaining: 331ms
564:	learn: 0.4769062	total: 429ms	remaining: 330ms
565:	learn: 0.4763789	total: 430ms	remaining: 329ms
566:	learn: 0.4755643	total: 430ms	remaining: 329ms
567:	learn: 0.4751969	total: 431ms	remaining: 328ms
568:	learn: 0.4750581	total: 432ms	remaining: 327ms
569:	learn: 0.4745658	total: 433ms	remaining: 326ms
570:	learn: 0.4740526	total: 434ms	remaining: 326ms
571:	learn: 0.4733774	total: 434ms	remaining: 325ms
572:	learn: 0.4727871	total: 435ms	remaining: 324ms
573:	learn: 0.4722164	total: 436ms	remaining: 323ms
574:	learn: 0.4720713	total: 436ms	remaining: 323ms
575:	learn: 0.4717433	total: 437ms	remaining: 322ms
576:	learn: 0.4710058	total: 438ms	remaining: 321ms
577:	learn: 0.4708067	total: 439ms	remaining: 320ms
578:	learn: 0.4704280	total: 439ms	remaining: 320ms
579:	learn: 0.4700042	total: 440ms	remaining: 319ms
580:	learn: 0.4698132	total: 441ms	remaining: 318ms
581:	learn: 0.4693709	total: 442ms	remaining: 317ms
582:	learn: 0.4693359	total: 443ms	remaining: 317ms
583:	learn: 0.4691283	total: 444ms	remaining: 316ms
584:	learn: 0.4685140	total: 444ms	remaining: 315ms
585:	learn: 0.4682188	total: 445ms	remaining: 315ms
586:	learn: 0.4681863	total: 446ms	remaining: 314ms
587:	learn: 0.4676812	total: 447ms	remaining: 313ms
588:	learn: 0.4671980	total: 448ms	remaining: 313ms
589:	learn: 0.4671368	total: 449ms	remaining: 312ms
590:	learn: 0.4665974	total: 450ms	remaining: 311ms
591:	learn: 0.4665378	total: 450ms	remaining: 310ms
592:	learn: 0.4658390	total: 451ms	remaining: 310ms
593:	learn: 0.4647839	total: 452ms	remaining: 309ms
594:	learn: 0.4645387	total: 453ms	remaining: 308ms
595:	learn: 0.4642744	total: 454ms	remaining: 307ms
596:	learn: 0.4632549	total: 454ms	remaining: 307ms
597:	learn: 0.4628143	total: 455ms	remaining: 306ms
598:	learn: 0.4622122	total: 456ms	remaining: 305ms
599:	learn: 0.4617447	total: 457ms	remaining: 304ms
600:	learn: 0.4617014	total: 457ms	remaining: 304ms
601:	learn: 0.4615462	total: 458ms	remaining: 303ms
602:	learn: 0.4607832	total: 459ms	remaining: 302ms
603:	learn: 0.4604603	total: 460ms	remaining: 302ms
604:	learn: 0.4599586	total: 461ms	remaining: 301ms
605:	learn: 0.4597612	total: 462ms	remaining: 300ms
606:	learn: 0.4595534	total: 462ms	remaining: 299ms
607:	learn: 0.4594810	total: 463ms	remaining: 299ms
608:	learn: 0.4592328	total: 464ms	remaining: 298ms
609:	learn: 0.4587733	total: 465ms	remaining: 297ms
610:	learn: 0.4583532	total: 465ms	remaining: 296ms
611:	learn: 0.4579265	total: 466ms	remaining: 296ms
612:	learn: 0.4578318	total: 467ms	remaining: 295ms
613:	learn: 0.4574796	total: 468ms	remaining: 294ms
614:	learn: 0.4574161	total: 469ms	remaining: 293ms
615:	learn: 0.4572132	total: 469ms	remaining: 293ms
616:	learn: 0.4565064	total: 470ms	remaining: 292ms
617:	learn: 0.4560728	total: 471ms	remaining: 291ms
618:	learn: 0.4555573	total: 472ms	remaining: 290ms
619:	learn: 0.4553341	total: 472ms	remaining: 290ms
620:	learn: 0.4550705	total: 473ms	remaining: 289ms
621:	learn: 0.4541975	total: 474ms	remaining: 288ms
622:	learn: 0.4534771	total: 475ms	remaining: 287ms
623:	learn: 0.4534476	total: 475ms	remaining: 286ms
624:	learn: 0.4529232	total: 476ms	remaining: 286ms
625:	learn: 0.4527754	total: 477ms	remaining: 285ms
626:	learn: 0.4520531	total: 478ms	remaining: 284ms
627:	learn: 0.4512809	total: 478ms	remaining: 283ms
628:	learn: 0.4510563	total: 479ms	remaining: 283ms
629:	learn: 0.4506225	total: 480ms	remaining: 282ms
630:	learn: 0.4502924	total: 481ms	remaining: 281ms
631:	learn: 0.4498753	total: 481ms	remaining: 280ms
632:	learn: 0.4494335	total: 482ms	remaining: 280ms
633:	learn: 0.4490512	total: 483ms	remaining: 279ms
634:	learn: 0.4485665	total: 484ms	remaining: 278ms
635:	learn: 0.4481106	total: 484ms	remaining: 277ms
636:	learn: 0.4477019	total: 485ms	remaining: 276ms
637:	learn: 0.4472271	total: 486ms	remaining: 276ms
638:	learn: 0.4462977	total: 487ms	remaining: 275ms
639:	learn: 0.4461717	total: 487ms	remaining: 274ms
640:	learn: 0.4460872	total: 488ms	remaining: 273ms
641:	learn: 0.4455484	total: 489ms	remaining: 273ms
642:	learn: 0.4453727	total: 490ms	remaining: 272ms
643:	learn: 0.4451869	total: 490ms	remaining: 271ms
644:	learn: 0.4445433	total: 491ms	remaining: 270ms
645:	learn: 0.4441202	total: 492ms	remaining: 270ms
646:	learn: 0.4439314	total: 493ms	remaining: 269ms
647:	learn: 0.4430636	total: 493ms	remaining: 268ms
648:	learn: 0.4426169	total: 494ms	remaining: 267ms
649:	learn: 0.4420852	total: 495ms	remaining: 267ms
650:	learn: 0.4417796	total: 496ms	remaining: 266ms
651:	learn: 0.4410359	total: 497ms	remaining: 265ms
652:	learn: 0.4404223	total: 497ms	remaining: 264ms
653:	learn: 0.4399157	total: 498ms	remaining: 264ms
654:	learn: 0.4397396	total: 499ms	remaining: 263ms
655:	learn: 0.4387805	total: 500ms	remaining: 262ms
656:	learn: 0.4385772	total: 500ms	remaining: 261ms
657:	learn: 0.4380708	total: 501ms	remaining: 260ms
658:	learn: 0.4377037	total: 502ms	remaining: 260ms
659:	learn: 0.4374376	total: 502ms	remaining: 259ms
660:	learn: 0.4365986	total: 503ms	remaining: 258ms
661:	learn: 0.4359346	total: 504ms	remaining: 257ms
662:	learn: 0.4354588	total: 505ms	remaining: 257ms
663:	learn: 0.4348411	total: 505ms	remaining: 256ms
664:	learn: 0.4343056	total: 506ms	remaining: 255ms
665:	learn: 0.4339117	total: 507ms	remaining: 254ms
666:	learn: 0.4336593	total: 508ms	remaining: 253ms
667:	learn: 0.4335961	total: 508ms	remaining: 253ms
668:	learn: 0.4330852	total: 509ms	remaining: 252ms
669:	learn: 0.4327057	total: 510ms	remaining: 251ms
670:	learn: 0.4321868	total: 511ms	remaining: 250ms
671:	learn: 0.4321159	total: 511ms	remaining: 250ms
672:	learn: 0.4319790	total: 512ms	remaining: 249ms
673:	learn: 0.4317789	total: 513ms	remaining: 248ms
674:	learn: 0.4314417	total: 514ms	remaining: 247ms
675:	learn: 0.4310778	total: 514ms	remaining: 247ms
676:	learn: 0.4307673	total: 515ms	remaining: 246ms
677:	learn: 0.4305329	total: 516ms	remaining: 245ms
678:	learn: 0.4302574	total: 517ms	remaining: 244ms
679:	learn: 0.4301068	total: 517ms	remaining: 243ms
680:	learn: 0.4296968	total: 518ms	remaining: 243ms
681:	learn: 0.4293552	total: 519ms	remaining: 242ms
682:	learn: 0.4287197	total: 520ms	remaining: 241ms
683:	learn: 0.4281278	total: 520ms	remaining: 240ms
684:	learn: 0.4279521	total: 521ms	remaining: 240ms
685:	learn: 0.4271713	total: 522ms	remaining: 239ms
686:	learn: 0.4270711	total: 523ms	remaining: 238ms
687:	learn: 0.4267525	total: 523ms	remaining: 237ms
688:	learn: 0.4262109	total: 524ms	remaining: 237ms
689:	learn: 0.4259546	total: 525ms	remaining: 236ms
690:	learn: 0.4254118	total: 526ms	remaining: 235ms
691:	learn: 0.4248703	total: 526ms	remaining: 234ms
692:	learn: 0.4243772	total: 527ms	remaining: 234ms
693:	learn: 0.4240742	total: 528ms	remaining: 233ms
694:	learn: 0.4235727	total: 529ms	remaining: 232ms
695:	learn: 0.4230020	total: 529ms	remaining: 231ms
696:	learn: 0.4225705	total: 530ms	remaining: 230ms
697:	learn: 0.4216761	total: 531ms	remaining: 230ms
698:	learn: 0.4215949	total: 531ms	remaining: 229ms
699:	learn: 0.4208980	total: 532ms	remaining: 228ms
700:	learn: 0.4204518	total: 533ms	remaining: 227ms
701:	learn: 0.4201265	total: 534ms	remaining: 227ms
702:	learn: 0.4199209	total: 535ms	remaining: 226ms
703:	learn: 0.4194258	total: 535ms	remaining: 225ms
704:	learn: 0.4189918	total: 536ms	remaining: 224ms
705:	learn: 0.4186303	total: 537ms	remaining: 224ms
706:	learn: 0.4181509	total: 538ms	remaining: 223ms
707:	learn: 0.4175256	total: 540ms	remaining: 223ms
708:	learn: 0.4174122	total: 541ms	remaining: 222ms
709:	learn: 0.4171363	total: 542ms	remaining: 221ms
710:	learn: 0.4168289	total: 542ms	remaining: 220ms
711:	learn: 0.4165059	total: 543ms	remaining: 220ms
712:	learn: 0.4162713	total: 544ms	remaining: 219ms
713:	learn: 0.4161732	total: 545ms	remaining: 218ms
714:	learn: 0.4160914	total: 546ms	remaining: 217ms
715:	learn: 0.4158504	total: 546ms	remaining: 217ms
716:	learn: 0.4156086	total: 547ms	remaining: 216ms
717:	learn: 0.4152907	total: 548ms	remaining: 215ms
718:	learn: 0.4151987	total: 549ms	remaining: 214ms
719:	learn: 0.4149667	total: 549ms	remaining: 214ms
720:	learn: 0.4147047	total: 550ms	remaining: 213ms
721:	learn: 0.4144971	total: 551ms	remaining: 212ms
722:	learn: 0.4140480	total: 552ms	remaining: 211ms
723:	learn: 0.4137613	total: 553ms	remaining: 211ms
724:	learn: 0.4133772	total: 553ms	remaining: 210ms
725:	learn: 0.4130752	total: 554ms	remaining: 209ms
726:	learn: 0.4123384	total: 555ms	remaining: 208ms
727:	learn: 0.4116938	total: 556ms	remaining: 208ms
728:	learn: 0.4114524	total: 556ms	remaining: 207ms
729:	learn: 0.4106433	total: 557ms	remaining: 206ms
730:	learn: 0.4104496	total: 558ms	remaining: 205ms
731:	learn: 0.4104119	total: 559ms	remaining: 205ms
732:	learn: 0.4101384	total: 560ms	remaining: 204ms
733:	learn: 0.4099731	total: 560ms	remaining: 203ms
734:	learn: 0.4096467	total: 561ms	remaining: 202ms
735:	learn: 0.4094232	total: 562ms	remaining: 202ms
736:	learn: 0.4091496	total: 563ms	remaining: 201ms
737:	learn: 0.4090367	total: 564ms	remaining: 200ms
738:	learn: 0.4089849	total: 564ms	remaining: 199ms
739:	learn: 0.4088765	total: 565ms	remaining: 199ms
740:	learn: 0.4084587	total: 566ms	remaining: 198ms
741:	learn: 0.4081011	total: 567ms	remaining: 197ms
742:	learn: 0.4079431	total: 567ms	remaining: 196ms
743:	learn: 0.4077670	total: 568ms	remaining: 195ms
744:	learn: 0.4075018	total: 569ms	remaining: 195ms
745:	learn: 0.4070240	total: 570ms	remaining: 194ms
746:	learn: 0.4066487	total: 570ms	remaining: 193ms
747:	learn: 0.4060609	total: 571ms	remaining: 192ms
748:	learn: 0.4057731	total: 572ms	remaining: 192ms
749:	learn: 0.4057434	total: 573ms	remaining: 191ms
750:	learn: 0.4050542	total: 574ms	remaining: 190ms
751:	learn: 0.4047785	total: 574ms	remaining: 189ms
752:	learn: 0.4043897	total: 575ms	remaining: 189ms
753:	learn: 0.4042380	total: 576ms	remaining: 188ms
754:	learn: 0.4036504	total: 577ms	remaining: 187ms
755:	learn: 0.4034943	total: 577ms	remaining: 186ms
756:	learn: 0.4032493	total: 578ms	remaining: 186ms
757:	learn: 0.4026174	total: 579ms	remaining: 185ms
758:	learn: 0.4022981	total: 580ms	remaining: 184ms
759:	learn: 0.4017510	total: 581ms	remaining: 183ms
760:	learn: 0.4013180	total: 582ms	remaining: 183ms
761:	learn: 0.4009383	total: 583ms	remaining: 182ms
762:	learn: 0.4005834	total: 583ms	remaining: 181ms
763:	learn: 0.4001978	total: 584ms	remaining: 180ms
764:	learn: 0.3993830	total: 585ms	remaining: 180ms
765:	learn: 0.3991346	total: 586ms	remaining: 179ms
766:	learn: 0.3989916	total: 587ms	remaining: 178ms
767:	learn: 0.3984177	total: 588ms	remaining: 178ms
768:	learn: 0.3979980	total: 588ms	remaining: 177ms
769:	learn: 0.3979567	total: 589ms	remaining: 176ms
770:	learn: 0.3976760	total: 590ms	remaining: 175ms
771:	learn: 0.3971616	total: 591ms	remaining: 175ms
772:	learn: 0.3971226	total: 592ms	remaining: 174ms
773:	learn: 0.3967103	total: 592ms	remaining: 173ms
774:	learn: 0.3964716	total: 593ms	remaining: 172ms
775:	learn: 0.3960547	total: 594ms	remaining: 172ms
776:	learn: 0.3956811	total: 595ms	remaining: 171ms
777:	learn: 0.3950635	total: 596ms	remaining: 170ms
778:	learn: 0.3948112	total: 597ms	remaining: 169ms
779:	learn: 0.3944991	total: 598ms	remaining: 169ms
780:	learn: 0.3940232	total: 598ms	remaining: 168ms
781:	learn: 0.3939916	total: 599ms	remaining: 167ms
782:	learn: 0.3935230	total: 600ms	remaining: 166ms
783:	learn: 0.3932668	total: 601ms	remaining: 166ms
784:	learn: 0.3927345	total: 602ms	remaining: 165ms
785:	learn: 0.3925586	total: 602ms	remaining: 164ms
786:	learn: 0.3922634	total: 603ms	remaining: 163ms
787:	learn: 0.3922130	total: 604ms	remaining: 162ms
788:	learn: 0.3918889	total: 604ms	remaining: 162ms
789:	learn: 0.3916216	total: 605ms	remaining: 161ms
790:	learn: 0.3913986	total: 606ms	remaining: 160ms
791:	learn: 0.3908850	total: 607ms	remaining: 159ms
792:	learn: 0.3903327	total: 608ms	remaining: 159ms
793:	learn: 0.3899757	total: 608ms	remaining: 158ms
794:	learn: 0.3898182	total: 609ms	remaining: 157ms
795:	learn: 0.3895856	total: 610ms	remaining: 156ms
796:	learn: 0.3889957	total: 611ms	remaining: 156ms
797:	learn: 0.3889225	total: 611ms	remaining: 155ms
798:	learn: 0.3885116	total: 612ms	remaining: 154ms
799:	learn: 0.3881164	total: 613ms	remaining: 153ms
800:	learn: 0.3878359	total: 614ms	remaining: 153ms
801:	learn: 0.3872712	total: 615ms	remaining: 152ms
802:	learn: 0.3871354	total: 616ms	remaining: 151ms
803:	learn: 0.3869802	total: 617ms	remaining: 150ms
804:	learn: 0.3865208	total: 617ms	remaining: 150ms
805:	learn: 0.3860549	total: 618ms	remaining: 149ms
806:	learn: 0.3858202	total: 619ms	remaining: 148ms
807:	learn: 0.3850772	total: 620ms	remaining: 147ms
808:	learn: 0.3848451	total: 621ms	remaining: 147ms
809:	learn: 0.3847171	total: 622ms	remaining: 146ms
810:	learn: 0.3846033	total: 622ms	remaining: 145ms
811:	learn: 0.3844535	total: 623ms	remaining: 144ms
812:	learn: 0.3842013	total: 624ms	remaining: 144ms
813:	learn: 0.3841604	total: 625ms	remaining: 143ms
814:	learn: 0.3839062	total: 626ms	remaining: 142ms
815:	learn: 0.3834123	total: 626ms	remaining: 141ms
816:	learn: 0.3832695	total: 627ms	remaining: 140ms
817:	learn: 0.3829096	total: 628ms	remaining: 140ms
818:	learn: 0.3825355	total: 629ms	remaining: 139ms
819:	learn: 0.3823536	total: 629ms	remaining: 138ms
820:	learn: 0.3818823	total: 630ms	remaining: 137ms
821:	learn: 0.3818563	total: 631ms	remaining: 137ms
822:	learn: 0.3813571	total: 632ms	remaining: 136ms
823:	learn: 0.3810426	total: 633ms	remaining: 135ms
824:	learn: 0.3805368	total: 633ms	remaining: 134ms
825:	learn: 0.3797824	total: 634ms	remaining: 134ms
826:	learn: 0.3795563	total: 635ms	remaining: 133ms
827:	learn: 0.3789630	total: 636ms	remaining: 132ms
828:	learn: 0.3789054	total: 637ms	remaining: 131ms
829:	learn: 0.3787864	total: 637ms	remaining: 131ms
830:	learn: 0.3784262	total: 638ms	remaining: 130ms
831:	learn: 0.3780193	total: 639ms	remaining: 129ms
832:	learn: 0.3777673	total: 640ms	remaining: 128ms
833:	learn: 0.3774043	total: 640ms	remaining: 127ms
834:	learn: 0.3772649	total: 641ms	remaining: 127ms
835:	learn: 0.3771082	total: 642ms	remaining: 126ms
836:	learn: 0.3766326	total: 643ms	remaining: 125ms
837:	learn: 0.3761438	total: 643ms	remaining: 124ms
838:	learn: 0.3759537	total: 644ms	remaining: 124ms
839:	learn: 0.3757300	total: 645ms	remaining: 123ms
840:	learn: 0.3756585	total: 646ms	remaining: 122ms
841:	learn: 0.3750942	total: 646ms	remaining: 121ms
842:	learn: 0.3749327	total: 647ms	remaining: 120ms
843:	learn: 0.3744390	total: 648ms	remaining: 120ms
844:	learn: 0.3743015	total: 648ms	remaining: 119ms
845:	learn: 0.3741093	total: 649ms	remaining: 118ms
846:	learn: 0.3738041	total: 650ms	remaining: 117ms
847:	learn: 0.3736516	total: 651ms	remaining: 117ms
848:	learn: 0.3729339	total: 651ms	remaining: 116ms
849:	learn: 0.3727763	total: 652ms	remaining: 115ms
850:	learn: 0.3724402	total: 653ms	remaining: 114ms
851:	learn: 0.3721654	total: 654ms	remaining: 114ms
852:	learn: 0.3717962	total: 654ms	remaining: 113ms
853:	learn: 0.3715101	total: 655ms	remaining: 112ms
854:	learn: 0.3713717	total: 656ms	remaining: 111ms
855:	learn: 0.3711470	total: 657ms	remaining: 110ms
856:	learn: 0.3707077	total: 657ms	remaining: 110ms
857:	learn: 0.3706613	total: 658ms	remaining: 109ms
858:	learn: 0.3702945	total: 659ms	remaining: 108ms
859:	learn: 0.3699757	total: 660ms	remaining: 107ms
860:	learn: 0.3696916	total: 661ms	remaining: 107ms
861:	learn: 0.3693972	total: 661ms	remaining: 106ms
862:	learn: 0.3692800	total: 662ms	remaining: 105ms
863:	learn: 0.3687756	total: 663ms	remaining: 104ms
864:	learn: 0.3684219	total: 664ms	remaining: 104ms
865:	learn: 0.3683022	total: 664ms	remaining: 103ms
866:	learn: 0.3681731	total: 665ms	remaining: 102ms
867:	learn: 0.3678136	total: 666ms	remaining: 101ms
868:	learn: 0.3676195	total: 667ms	remaining: 100ms
869:	learn: 0.3672785	total: 667ms	remaining: 99.7ms
870:	learn: 0.3670484	total: 668ms	remaining: 98.9ms
871:	learn: 0.3668865	total: 669ms	remaining: 98.2ms
872:	learn: 0.3667554	total: 670ms	remaining: 97.4ms
873:	learn: 0.3666150	total: 670ms	remaining: 96.6ms
874:	learn: 0.3663481	total: 671ms	remaining: 95.9ms
875:	learn: 0.3656486	total: 672ms	remaining: 95.1ms
876:	learn: 0.3652244	total: 673ms	remaining: 94.3ms
877:	learn: 0.3649764	total: 673ms	remaining: 93.6ms
878:	learn: 0.3647681	total: 674ms	remaining: 92.8ms
879:	learn: 0.3642386	total: 675ms	remaining: 92ms
880:	learn: 0.3640111	total: 676ms	remaining: 91.2ms
881:	learn: 0.3636933	total: 676ms	remaining: 90.5ms
882:	learn: 0.3633552	total: 677ms	remaining: 89.7ms
883:	learn: 0.3627811	total: 678ms	remaining: 88.9ms
884:	learn: 0.3624149	total: 678ms	remaining: 88.2ms
885:	learn: 0.3620926	total: 679ms	remaining: 87.4ms
886:	learn: 0.3619023	total: 680ms	remaining: 86.6ms
887:	learn: 0.3616650	total: 681ms	remaining: 85.9ms
888:	learn: 0.3613533	total: 682ms	remaining: 85.1ms
889:	learn: 0.3613328	total: 682ms	remaining: 84.3ms
890:	learn: 0.3609592	total: 683ms	remaining: 83.6ms
891:	learn: 0.3609387	total: 684ms	remaining: 82.8ms
892:	learn: 0.3605361	total: 685ms	remaining: 82ms
893:	learn: 0.3605251	total: 685ms	remaining: 81.3ms
894:	learn: 0.3600991	total: 686ms	remaining: 80.5ms
895:	learn: 0.3598772	total: 687ms	remaining: 79.7ms
896:	learn: 0.3597275	total: 687ms	remaining: 78.9ms
897:	learn: 0.3593858	total: 688ms	remaining: 78.2ms
898:	learn: 0.3593150	total: 689ms	remaining: 77.4ms
899:	learn: 0.3588685	total: 690ms	remaining: 76.6ms
900:	learn: 0.3581683	total: 691ms	remaining: 75.9ms
901:	learn: 0.3575239	total: 691ms	remaining: 75.1ms
902:	learn: 0.3574521	total: 692ms	remaining: 74.3ms
903:	learn: 0.3573017	total: 693ms	remaining: 73.6ms
904:	learn: 0.3571320	total: 694ms	remaining: 72.8ms
905:	learn: 0.3570777	total: 695ms	remaining: 72.1ms
906:	learn: 0.3567374	total: 695ms	remaining: 71.3ms
907:	learn: 0.3564322	total: 696ms	remaining: 70.5ms
908:	learn: 0.3561054	total: 697ms	remaining: 69.8ms
909:	learn: 0.3558947	total: 698ms	remaining: 69ms
910:	learn: 0.3553490	total: 699ms	remaining: 68.2ms
911:	learn: 0.3550062	total: 699ms	remaining: 67.5ms
912:	learn: 0.3545275	total: 700ms	remaining: 66.7ms
913:	learn: 0.3542440	total: 701ms	remaining: 65.9ms
914:	learn: 0.3540626	total: 702ms	remaining: 65.2ms
915:	learn: 0.3537182	total: 702ms	remaining: 64.4ms
916:	learn: 0.3534090	total: 703ms	remaining: 63.6ms
917:	learn: 0.3531339	total: 704ms	remaining: 62.9ms
918:	learn: 0.3526459	total: 705ms	remaining: 62.1ms
919:	learn: 0.3523828	total: 705ms	remaining: 61.3ms
920:	learn: 0.3523662	total: 706ms	remaining: 60.6ms
921:	learn: 0.3521686	total: 707ms	remaining: 59.8ms
922:	learn: 0.3518144	total: 708ms	remaining: 59ms
923:	learn: 0.3515664	total: 708ms	remaining: 58.3ms
924:	learn: 0.3512271	total: 709ms	remaining: 57.5ms
925:	learn: 0.3509670	total: 710ms	remaining: 56.7ms
926:	learn: 0.3508352	total: 711ms	remaining: 56ms
927:	learn: 0.3503711	total: 711ms	remaining: 55.2ms
928:	learn: 0.3498563	total: 712ms	remaining: 54.4ms
929:	learn: 0.3498258	total: 713ms	remaining: 53.7ms
930:	learn: 0.3497408	total: 714ms	remaining: 52.9ms
931:	learn: 0.3494233	total: 714ms	remaining: 52.1ms
932:	learn: 0.3493206	total: 715ms	remaining: 51.3ms
933:	learn: 0.3486571	total: 716ms	remaining: 50.6ms
934:	learn: 0.3484682	total: 717ms	remaining: 49.8ms
935:	learn: 0.3481733	total: 717ms	remaining: 49ms
936:	learn: 0.3479573	total: 718ms	remaining: 48.3ms
937:	learn: 0.3476724	total: 719ms	remaining: 47.5ms
938:	learn: 0.3473794	total: 720ms	remaining: 46.7ms
939:	learn: 0.3471748	total: 720ms	remaining: 46ms
940:	learn: 0.3467268	total: 721ms	remaining: 45.2ms
941:	learn: 0.3464485	total: 722ms	remaining: 44.4ms
942:	learn: 0.3461014	total: 723ms	remaining: 43.7ms
943:	learn: 0.3459388	total: 723ms	remaining: 42.9ms
944:	learn: 0.3456302	total: 724ms	remaining: 42.1ms
945:	learn: 0.3453055	total: 725ms	remaining: 41.4ms
946:	learn: 0.3449329	total: 726ms	remaining: 40.6ms
947:	learn: 0.3446257	total: 727ms	remaining: 39.9ms
948:	learn: 0.3443995	total: 728ms	remaining: 39.1ms
949:	learn: 0.3440676	total: 728ms	remaining: 38.3ms
950:	learn: 0.3438826	total: 729ms	remaining: 37.6ms
951:	learn: 0.3436952	total: 730ms	remaining: 36.8ms
952:	learn: 0.3436363	total: 731ms	remaining: 36ms
953:	learn: 0.3435132	total: 732ms	remaining: 35.3ms
954:	learn: 0.3433030	total: 732ms	remaining: 34.5ms
955:	learn: 0.3431099	total: 733ms	remaining: 33.8ms
956:	learn: 0.3425005	total: 734ms	remaining: 33ms
957:	learn: 0.3421401	total: 735ms	remaining: 32.2ms
958:	learn: 0.3419544	total: 736ms	remaining: 31.5ms
959:	learn: 0.3417078	total: 737ms	remaining: 30.7ms
960:	learn: 0.3416033	total: 738ms	remaining: 29.9ms
961:	learn: 0.3415697	total: 738ms	remaining: 29.2ms
962:	learn: 0.3410846	total: 739ms	remaining: 28.4ms
963:	learn: 0.3407857	total: 740ms	remaining: 27.6ms
964:	learn: 0.3407272	total: 741ms	remaining: 26.9ms
965:	learn: 0.3405795	total: 742ms	remaining: 26.1ms
966:	learn: 0.3405171	total: 742ms	remaining: 25.3ms
967:	learn: 0.3402860	total: 743ms	remaining: 24.6ms
968:	learn: 0.3400220	total: 744ms	remaining: 23.8ms
969:	learn: 0.3397058	total: 745ms	remaining: 23ms
970:	learn: 0.3394919	total: 745ms	remaining: 22.3ms
971:	learn: 0.3394805	total: 746ms	remaining: 21.5ms
972:	learn: 0.3391074	total: 747ms	remaining: 20.7ms
973:	learn: 0.3387956	total: 748ms	remaining: 20ms
974:	learn: 0.3384962	total: 749ms	remaining: 19.2ms
975:	learn: 0.3382599	total: 749ms	remaining: 18.4ms
976:	learn: 0.3379917	total: 750ms	remaining: 17.7ms
977:	learn: 0.3378238	total: 751ms	remaining: 16.9ms
978:	learn: 0.3378088	total: 752ms	remaining: 16.1ms
979:	learn: 0.3373772	total: 753ms	remaining: 15.4ms
980:	learn: 0.3371184	total: 754ms	remaining: 14.6ms
981:	learn: 0.3369178	total: 754ms	remaining: 13.8ms
982:	learn: 0.3366802	total: 755ms	remaining: 13.1ms
983:	learn: 0.3366562	total: 756ms	remaining: 12.3ms
984:	learn: 0.3363874	total: 757ms	remaining: 11.5ms
985:	learn: 0.3362072	total: 757ms	remaining: 10.8ms
986:	learn: 0.3359058	total: 758ms	remaining: 9.99ms
987:	learn: 0.3353623	total: 759ms	remaining: 9.22ms
988:	learn: 0.3349687	total: 760ms	remaining: 8.45ms
989:	learn: 0.3349059	total: 761ms	remaining: 7.68ms
990:	learn: 0.3348006	total: 761ms	remaining: 6.91ms
991:	learn: 0.3347004	total: 762ms	remaining: 6.14ms
992:	learn: 0.3345055	total: 763ms	remaining: 5.38ms
993:	learn: 0.3344524	total: 764ms	remaining: 4.61ms
994:	learn: 0.3341144	total: 764ms	remaining: 3.84ms
995:	learn: 0.3337589	total: 765ms	remaining: 3.07ms
996:	learn: 0.3335552	total: 766ms	remaining: 2.3ms
997:	learn: 0.3333652	total: 767ms	remaining: 1.54ms
998:	learn: 0.3331609	total: 767ms	remaining: 768us
999:	learn: 0.3330577	total: 768ms	remaining: 0us

visualize_error(error, modelname)

The Error is still high at begigining of the dataset which we found earlier that they are problamatic records.

visulaize_performance_of_the_model(pred, y_test, modelname)

Some datapoints are far away from perfect line.

visualize_prediction_on_traindata(pred_cbr_trn,  y_train, modelname)

r2_score(y_test, pred)

0.6900771346347321

r2_score(y_train, pred_cbr_trn)

0.9520182384397772

Still the model is overfitted on training set.

Let's try another approach to find better train & test split.

Approach 2:The approach is First 80% of the Desending order of failure records were fed into training part and rest 20% of records were fed into testing part.

I have to clear one thing here...

We're keep on changing the approach but not the dataset. We have'nt changed anything in the dataset after the removal of duplicates. We're keep trying to get a Generalized model for this dataset. From all above visualization, we can confirm that Random Train & Test split is purely Underfitted for this Dataset .That's why we're trying it with different approach.

We know clearly that the failure records when comes into testing part, definitely fails to predict and gives a huge error.

data_check

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50	Count of Failure
0	2.841	0.880	1.705	0	3	0.226	1.647	648.0
1	2.031	0.872	1.475	0	1	0.202	6.424	644.0
2	1.094	1.236	1.461	0	1	0.996	1.911	633.0
3	3.739	0.000	1.250	1	2	3.267	2.149	629.0
4	3.833	0.405	1.522	0	1	3.492	2.092	627.0
...	...	...	...	...	...	...	...	...
686	3.900	0.429	1.572	0	1	2.297	3.842	0.0
687	2.800	0.693	1.091	0	1	1.437	3.603	0.0
688	2.591	0.331	1.629	0	0	0.874	2.395	0.0
689	1.279	1.327	1.284	0	0	2.200	4.697	0.0
690	1.822	0.681	0.794	0	0	2.335	3.696	0.0

691 rows × 8 columns

train = data_check.iloc[: int(len(data_check) * 0.8), :]

train

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50	Count of Failure
0	2.841	0.880	1.705	0	3	0.226	1.647	648.0
1	2.031	0.872	1.475	0	1	0.202	6.424	644.0
2	1.094	1.236	1.461	0	1	0.996	1.911	633.0
3	3.739	0.000	1.250	1	2	3.267	2.149	629.0
4	3.833	0.405	1.522	0	1	3.492	2.092	627.0
...	...	...	...	...	...	...	...	...
547	2.866	0.223	1.333	0	1	1.050	2.270	0.0
548	3.080	0.223	1.385	0	0	1.195	2.070	0.0
549	2.260	0.499	0.907	0	0	2.876	3.645	0.0
550	2.910	0.000	1.000	0	0	2.608	3.447	0.0
551	2.260	0.604	0.836	0	0	3.045	4.194	0.0

552 rows × 8 columns

test = data_check.iloc[int(len(data_check) * 0.8):, :]
test

	CIC0	SM1_Dz(Z)	GATS1i	NdsCH	NdssC	MLOGP	LC50	Count of Failure
552	2.126	0.405	1.690	1	1	0.479	3.573	0.0
553	1.940	0.749	1.066	0	0	1.492	2.990	0.0
554	3.802	0.405	1.527	1	0	1.869	3.700	0.0
555	1.512	0.331	1.627	1	0	-0.386	2.891	0.0
556	2.560	0.134	1.758	0	0	0.347	2.283	0.0
...	...	...	...	...	...	...	...	...
686	3.900	0.429	1.572	0	1	2.297	3.842	0.0
687	2.800	0.693	1.091	0	1	1.437	3.603	0.0
688	2.591	0.331	1.629	0	0	0.874	2.395	0.0
689	1.279	1.327	1.284	0	0	2.200	4.697	0.0
690	1.822	0.681	0.794	0	0	2.335	3.696	0.0

139 rows × 8 columns

len(train), len(test)

(552, 139)

x_train, y_train = train.drop(['Count of Failure', 'LC50'], axis = 1), train['LC50']
x_test,y_test = test.drop(['Count of Failure', 'LC50'], axis = 1), test['LC50']
cbr = CatBoostRegressor(verbose=0).fit(x_train, y_train)
pred = cbr.predict(x_test)
pred_cbr_trn = cbr.predict(x_train)
modelname = 'CatBoostRegressor Custom New'
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred, y_test)

visualize_error(error, modelname)

visulaize_performance_of_the_model(pred, y_test, modelname)

visualize_prediction_on_traindata(pred_cbr_trn,  y_train, modelname)

r2_score(y_test, pred)

0.8298781455616748

r2_score(y_train, pred_cbr_trn)

0.9483897799155157

x_train, y_train = train.drop(['Count of Failure', 'LC50'], axis = 1), train['LC50']
x_test,y_test = test.drop(['Count of Failure', 'LC50'], axis = 1), test['LC50']
cbr = CatBoostRegressor(depth=5,verbose=0).fit(x_train, y_train)
pred = cbr.predict(x_test)
pred_cbr_trn = cbr.predict(x_train)
modelname = 'CatBoostRegressor Custom New'
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred, y_test)

visualize_error(error, modelname)

visulaize_performance_of_the_model(pred, y_test, modelname)

visualize_prediction_on_traindata(pred_cbr_trn,  y_train, modelname)

r2_score(y_test, pred)

0.8438931806142868

r2_score(y_train, pred_cbr_trn)

0.9236252085280596

import plotly.figure_factory as ff
hist_data = [score_gbr, score_cbr, score_rfr, score_svr, score_mlr]
group_labels = ['GradientBoost Regressor',
                'CatBoostRegressor',
                'RandomForest Regressor',
                'SupportVector Regressor',
                'MultipleLinear Regression']
fig = ff.create_distplot(hist_data, group_labels=group_labels, show_hist=False, show_rug=False)
fig.show()

This is the reason why we're checking all approach and implemenation in one Algorithm i.e., CatBoostRegressor. The above normal distribution says the goodness of CatBoost Regressor.

CatBoost Regressor is fine tuned to get a generalised model.

rpt = pd.DataFrame(pd.read_csv('C:\\Users\\harip\\INEURON_PROJECTS\\Prediction of LC50\\LC50_Project\\data\\final_report\\final_report.csv',header=0))

rpt

	Unnamed: 0	Model Name	R2_Score(Training)	R2_Score_Testing	Depth	Iterations	Learning Rate
0	0	CatBoost Regressor Un-tuned	0.947378	0.846762	NaN	NaN	NaN
1	1	CatBoost Regressor Tuned	0.298614	0.492148	1.0	1000.0	0.001
2	2	CatBoost Regressor Tuned	0.539575	0.779213	1.0	1000.0	0.005
3	3	CatBoost Regressor Tuned	0.573510	0.810709	1.0	1000.0	0.007
4	4	CatBoost Regressor Tuned	0.596922	0.833277	1.0	1000.0	0.010
...	...	...	...	...	...	...	...
1496	1496	CatBoost Regressor Tuned	0.998506	0.816414	10.0	2000.0	0.030
1497	1497	CatBoost Regressor Tuned	0.999605	0.788437	10.0	2000.0	0.040
1498	1498	CatBoost Regressor Tuned	0.999864	0.786046	10.0	2000.0	0.050
1499	1499	CatBoost Regressor Tuned	0.999987	0.799946	10.0	2000.0	0.070
1500	1500	CatBoost Regressor Tuned	1.000000	0.785463	10.0	2000.0	0.100

1501 rows × 7 columns

report_cols = ['Model Name','R2_Score(Training)','R2_Score_Testing','Depth','Iterations','Learning Rate', 'Score Difference']
to_drop = [x for x in list(rpt.columns) if x not in report_cols]
rpt.drop(to_drop, axis=1, inplace=True)

rpt

	Model Name	R2_Score(Training)	R2_Score_Testing	Depth	Iterations	Learning Rate
0	CatBoost Regressor Un-tuned	0.947378	0.846762	NaN	NaN	NaN
1	CatBoost Regressor Tuned	0.298614	0.492148	1.0	1000.0	0.001
2	CatBoost Regressor Tuned	0.539575	0.779213	1.0	1000.0	0.005
3	CatBoost Regressor Tuned	0.573510	0.810709	1.0	1000.0	0.007
4	CatBoost Regressor Tuned	0.596922	0.833277	1.0	1000.0	0.010
...	...	...	...	...	...	...
1496	CatBoost Regressor Tuned	0.998506	0.816414	10.0	2000.0	0.030
1497	CatBoost Regressor Tuned	0.999605	0.788437	10.0	2000.0	0.040
1498	CatBoost Regressor Tuned	0.999864	0.786046	10.0	2000.0	0.050
1499	CatBoost Regressor Tuned	0.999987	0.799946	10.0	2000.0	0.070
1500	CatBoost Regressor Tuned	1.000000	0.785463	10.0	2000.0	0.100

1501 rows × 6 columns

rpt['Score Difference'] = list(rpt['R2_Score(Training)'] - rpt['R2_Score_Testing'])

rpt = rpt.loc[rpt['Score Difference']>=0]
rpt.sort_values(by='R2_Score_Testing', ascending=False,inplace=True)
rpt.reset_index(drop=True,inplace=True)

rpt

	Model Name	R2_Score(Training)	R2_Score_Testing	Depth	Iterations	Learning Rate	Score Difference
0	CatBoost Regressor Tuned	0.879607	0.878984	7.0	1550.0	0.010	0.000623
1	CatBoost Regressor Tuned	0.884010	0.877955	7.0	1600.0	0.010	0.006056
2	CatBoost Regressor Tuned	0.876529	0.876218	8.0	1250.0	0.010	0.000311
3	CatBoost Regressor Tuned	0.878928	0.876075	9.0	1000.0	0.010	0.002853
4	CatBoost Regressor Tuned	0.881049	0.875791	9.0	2000.0	0.005	0.005258
...	...	...	...	...	...	...	...
769	CatBoost Regressor Tuned	0.999945	0.774218	8.0	1750.0	0.100	0.225727
770	CatBoost Regressor Tuned	0.999979	0.773377	8.0	2000.0	0.100	0.226602
771	CatBoost Regressor Tuned	0.995980	0.772500	6.0	1750.0	0.070	0.223480
772	CatBoost Regressor Tuned	0.997405	0.768681	6.0	2000.0	0.070	0.228724
773	CatBoost Regressor Tuned	0.970011	0.767942	3.0	2000.0	0.100	0.202069

774 rows × 7 columns

depth = [1,2,3,4,5,6,7,8,9,10] iterations = [1000,1050,1100,1150,1200,1250,1300,1350,1400,1450,1500,1550,1600,1750,2000] learning_rate = [0.001,0.005,0.007,0.01,0.02,0.03,0.04,0.05,0.07,0.1] for i in range(len(depth)): for j in range(len(iterations)): for k in range(len(learning_rate)): tuned_cbr = CatBoostRegressor(depth=depth[i], iterations=iterations[j], learning_rate=learning_rate[k],verbose=0).fit(x_train,y_train) pred = tuned_cbr.predict(x_test) pred_y_train = tuned_cbr.predict(x_train) modelname.append('CatBoost Regressor Tuned') r2_score_train.append(r2_score(y_train, pred_y_train)) r2_score_test.append(r2_score(y_test, pred)) score_difference.append(r2_score(y_train, pred_y_train) - r2_score(y_test, pred)) depth_.append(depth[i]) iterations_.append(iterations[j]) learning_rate_.append(learning_rate[k]) report['Model Name'], report['R2_Score(Training)'], report['R2_Score_Testing'] = modelname, r2_score_train, r2_score_test report['Depth'], report['Iterations'], report['Learning Rate'] = depth_, iterations_, learning_rate_ Utility.create_directory('./data/final_report') report.to_csv('./data/final_report/final_report.csv')

The above code gives an report.csv in the particular folder of project.

From the Final Report, we generated filtered report with the condition of score diffrence greater than 0 is accpeted(To avoid underfitted model hyper-parameters). Then we sorted the R2 Scoring(Testing) as descending order. The first column gives a generalized model which implemented below.

cbr = CatBoostRegressor(depth=7,iterations=1550,learning_rate=0.01).fit(x_train,y_train)
pred = cbr.predict(x_test)
pred_cbr_trn = cbr.predict(x_train)
modelname = 'CatBoostRegressor Custom New'
error, zero_to_one, one_to_two, two_to_three, greater_than_three = calculate_error_range(pred, y_test)

0:	learn: 1.6245044	total: 2.03ms	remaining: 3.14s
1:	learn: 1.6178530	total: 3.71ms	remaining: 2.87s
2:	learn: 1.6111277	total: 5.14ms	remaining: 2.65s
3:	learn: 1.6044440	total: 6.44ms	remaining: 2.49s
4:	learn: 1.5972703	total: 7.98ms	remaining: 2.47s
5:	learn: 1.5904078	total: 9.22ms	remaining: 2.37s
6:	learn: 1.5832234	total: 10.5ms	remaining: 2.31s
7:	learn: 1.5763328	total: 11.7ms	remaining: 2.26s
8:	learn: 1.5701204	total: 12.9ms	remaining: 2.21s
9:	learn: 1.5633526	total: 14.1ms	remaining: 2.17s
10:	learn: 1.5566992	total: 15.3ms	remaining: 2.14s
11:	learn: 1.5504145	total: 16.5ms	remaining: 2.11s
12:	learn: 1.5441372	total: 17.6ms	remaining: 2.08s
13:	learn: 1.5379317	total: 18.7ms	remaining: 2.06s
14:	learn: 1.5321372	total: 20.1ms	remaining: 2.06s
15:	learn: 1.5262166	total: 21.3ms	remaining: 2.04s
16:	learn: 1.5201385	total: 22.6ms	remaining: 2.03s
17:	learn: 1.5137907	total: 23.8ms	remaining: 2.02s
18:	learn: 1.5079470	total: 25.1ms	remaining: 2.02s
19:	learn: 1.5017033	total: 26.3ms	remaining: 2.01s
20:	learn: 1.4956219	total: 27.6ms	remaining: 2.01s
21:	learn: 1.4896125	total: 28.9ms	remaining: 2s
22:	learn: 1.4838797	total: 30.1ms	remaining: 2s
23:	learn: 1.4773494	total: 31.4ms	remaining: 2s
24:	learn: 1.4712603	total: 32.6ms	remaining: 1.99s
25:	learn: 1.4657041	total: 33.7ms	remaining: 1.98s
26:	learn: 1.4603348	total: 34.9ms	remaining: 1.97s
27:	learn: 1.4551545	total: 36.1ms	remaining: 1.96s
28:	learn: 1.4496008	total: 37.3ms	remaining: 1.96s
29:	learn: 1.4444519	total: 38.4ms	remaining: 1.95s
30:	learn: 1.4390472	total: 39.9ms	remaining: 1.95s
31:	learn: 1.4337039	total: 41.1ms	remaining: 1.95s
32:	learn: 1.4289767	total: 42.3ms	remaining: 1.95s
33:	learn: 1.4241730	total: 43.5ms	remaining: 1.94s
34:	learn: 1.4188374	total: 44.7ms	remaining: 1.94s
35:	learn: 1.4137130	total: 45.9ms	remaining: 1.93s
36:	learn: 1.4093918	total: 47ms	remaining: 1.92s
37:	learn: 1.4045023	total: 47.9ms	remaining: 1.91s
38:	learn: 1.3998949	total: 49.1ms	remaining: 1.9s
39:	learn: 1.3952695	total: 50.4ms	remaining: 1.9s
40:	learn: 1.3916295	total: 50.9ms	remaining: 1.87s
41:	learn: 1.3866952	total: 52.1ms	remaining: 1.87s
42:	learn: 1.3820050	total: 53.4ms	remaining: 1.87s
43:	learn: 1.3774370	total: 54.6ms	remaining: 1.87s
44:	learn: 1.3725423	total: 55.8ms	remaining: 1.86s
45:	learn: 1.3678838	total: 56.9ms	remaining: 1.86s
46:	learn: 1.3632677	total: 58.1ms	remaining: 1.86s
47:	learn: 1.3585523	total: 59.5ms	remaining: 1.86s
48:	learn: 1.3543893	total: 60.6ms	remaining: 1.86s
49:	learn: 1.3500739	total: 61.8ms	remaining: 1.85s
50:	learn: 1.3457986	total: 63ms	remaining: 1.85s
51:	learn: 1.3411903	total: 64.4ms	remaining: 1.85s
52:	learn: 1.3375602	total: 64.9ms	remaining: 1.83s
53:	learn: 1.3332968	total: 66.1ms	remaining: 1.83s
54:	learn: 1.3294001	total: 67.3ms	remaining: 1.83s
55:	learn: 1.3248495	total: 68.5ms	remaining: 1.83s
56:	learn: 1.3205127	total: 69.7ms	remaining: 1.82s
57:	learn: 1.3164935	total: 70.9ms	remaining: 1.82s
58:	learn: 1.3126930	total: 72.1ms	remaining: 1.82s
59:	learn: 1.3096427	total: 72.5ms	remaining: 1.8s
60:	learn: 1.3055856	total: 73.8ms	remaining: 1.8s
61:	learn: 1.3013278	total: 75.1ms	remaining: 1.8s
62:	learn: 1.2974942	total: 76.3ms	remaining: 1.8s
63:	learn: 1.2934992	total: 77.5ms	remaining: 1.8s
64:	learn: 1.2898166	total: 78.8ms	remaining: 1.8s
65:	learn: 1.2863626	total: 79.9ms	remaining: 1.8s
66:	learn: 1.2825712	total: 81.1ms	remaining: 1.79s
67:	learn: 1.2785698	total: 82.4ms	remaining: 1.79s
68:	learn: 1.2749528	total: 83.5ms	remaining: 1.79s
69:	learn: 1.2711281	total: 84.7ms	remaining: 1.79s
70:	learn: 1.2672170	total: 85.9ms	remaining: 1.79s
71:	learn: 1.2636739	total: 86.6ms	remaining: 1.78s
72:	learn: 1.2601093	total: 87.7ms	remaining: 1.77s
73:	learn: 1.2565933	total: 88.9ms	remaining: 1.77s
74:	learn: 1.2528689	total: 90ms	remaining: 1.77s
75:	learn: 1.2496754	total: 91.2ms	remaining: 1.77s
76:	learn: 1.2470351	total: 91.9ms	remaining: 1.76s
77:	learn: 1.2438608	total: 93ms	remaining: 1.75s
78:	learn: 1.2402366	total: 94.1ms	remaining: 1.75s
79:	learn: 1.2368191	total: 95.4ms	remaining: 1.75s
80:	learn: 1.2332411	total: 96.5ms	remaining: 1.75s
81:	learn: 1.2298886	total: 97.6ms	remaining: 1.75s
82:	learn: 1.2266236	total: 98.7ms	remaining: 1.75s
83:	learn: 1.2233439	total: 99.9ms	remaining: 1.74s
84:	learn: 1.2201758	total: 101ms	remaining: 1.74s
85:	learn: 1.2167634	total: 102ms	remaining: 1.74s
86:	learn: 1.2134336	total: 103ms	remaining: 1.73s
87:	learn: 1.2103257	total: 104ms	remaining: 1.73s
88:	learn: 1.2073673	total: 105ms	remaining: 1.73s
89:	learn: 1.2048248	total: 106ms	remaining: 1.73s
90:	learn: 1.2019315	total: 108ms	remaining: 1.73s
91:	learn: 1.1989175	total: 109ms	remaining: 1.72s
92:	learn: 1.1957620	total: 110ms	remaining: 1.72s
93:	learn: 1.1928737	total: 111ms	remaining: 1.72s
94:	learn: 1.1897670	total: 112ms	remaining: 1.71s
95:	learn: 1.1868604	total: 113ms	remaining: 1.71s
96:	learn: 1.1836499	total: 114ms	remaining: 1.71s
97:	learn: 1.1811769	total: 115ms	remaining: 1.71s
98:	learn: 1.1786904	total: 117ms	remaining: 1.71s
99:	learn: 1.1758170	total: 118ms	remaining: 1.71s
100:	learn: 1.1729655	total: 119ms	remaining: 1.7s
101:	learn: 1.1705457	total: 120ms	remaining: 1.7s
102:	learn: 1.1680704	total: 121ms	remaining: 1.7s
103:	learn: 1.1652508	total: 122ms	remaining: 1.7s
104:	learn: 1.1631149	total: 124ms	remaining: 1.7s
105:	learn: 1.1603895	total: 125ms	remaining: 1.7s
106:	learn: 1.1576443	total: 126ms	remaining: 1.7s
107:	learn: 1.1551054	total: 127ms	remaining: 1.69s
108:	learn: 1.1525370	total: 128ms	remaining: 1.69s
109:	learn: 1.1500321	total: 129ms	remaining: 1.69s
110:	learn: 1.1475883	total: 130ms	remaining: 1.69s
111:	learn: 1.1450738	total: 131ms	remaining: 1.69s
112:	learn: 1.1428700	total: 133ms	remaining: 1.69s
113:	learn: 1.1405539	total: 134ms	remaining: 1.68s
114:	learn: 1.1380599	total: 135ms	remaining: 1.68s
115:	learn: 1.1355498	total: 136ms	remaining: 1.68s
116:	learn: 1.1333016	total: 137ms	remaining: 1.68s
117:	learn: 1.1310839	total: 138ms	remaining: 1.68s
118:	learn: 1.1289007	total: 139ms	remaining: 1.68s
119:	learn: 1.1264503	total: 141ms	remaining: 1.67s
120:	learn: 1.1241777	total: 142ms	remaining: 1.67s
121:	learn: 1.1218290	total: 143ms	remaining: 1.67s
122:	learn: 1.1195418	total: 144ms	remaining: 1.67s
123:	learn: 1.1172020	total: 145ms	remaining: 1.67s
124:	learn: 1.1150332	total: 146ms	remaining: 1.67s
125:	learn: 1.1127206	total: 147ms	remaining: 1.67s
126:	learn: 1.1105382	total: 148ms	remaining: 1.66s
127:	learn: 1.1086933	total: 150ms	remaining: 1.66s
128:	learn: 1.1063057	total: 151ms	remaining: 1.66s
129:	learn: 1.1040608	total: 152ms	remaining: 1.66s
130:	learn: 1.1019769	total: 153ms	remaining: 1.66s
131:	learn: 1.1002504	total: 154ms	remaining: 1.65s
132:	learn: 1.0989115	total: 154ms	remaining: 1.64s
133:	learn: 1.0968272	total: 155ms	remaining: 1.64s
134:	learn: 1.0947031	total: 156ms	remaining: 1.64s
135:	learn: 1.0923582	total: 157ms	remaining: 1.64s
136:	learn: 1.0904300	total: 159ms	remaining: 1.64s
137:	learn: 1.0887725	total: 160ms	remaining: 1.63s
138:	learn: 1.0871314	total: 161ms	remaining: 1.63s
139:	learn: 1.0852272	total: 162ms	remaining: 1.63s
140:	learn: 1.0834083	total: 163ms	remaining: 1.63s
141:	learn: 1.0815357	total: 164ms	remaining: 1.63s
142:	learn: 1.0793927	total: 165ms	remaining: 1.63s
143:	learn: 1.0776735	total: 166ms	remaining: 1.63s
144:	learn: 1.0758853	total: 168ms	remaining: 1.62s
145:	learn: 1.0740203	total: 169ms	remaining: 1.62s
146:	learn: 1.0719852	total: 170ms	remaining: 1.62s
147:	learn: 1.0701832	total: 171ms	remaining: 1.62s
148:	learn: 1.0682844	total: 172ms	remaining: 1.62s
149:	learn: 1.0664541	total: 173ms	remaining: 1.62s
150:	learn: 1.0645375	total: 174ms	remaining: 1.61s
151:	learn: 1.0627259	total: 175ms	remaining: 1.61s
152:	learn: 1.0607488	total: 177ms	remaining: 1.61s
153:	learn: 1.0589435	total: 178ms	remaining: 1.61s
154:	learn: 1.0570919	total: 179ms	remaining: 1.61s
155:	learn: 1.0550725	total: 180ms	remaining: 1.61s
156:	learn: 1.0536123	total: 181ms	remaining: 1.61s
157:	learn: 1.0521705	total: 182ms	remaining: 1.6s
158:	learn: 1.0507877	total: 183ms	remaining: 1.6s
159:	learn: 1.0493284	total: 184ms	remaining: 1.6s
160:	learn: 1.0475924	total: 186ms	remaining: 1.6s
161:	learn: 1.0464638	total: 187ms	remaining: 1.6s
162:	learn: 1.0450588	total: 188ms	remaining: 1.6s
163:	learn: 1.0439743	total: 189ms	remaining: 1.6s
164:	learn: 1.0425470	total: 190ms	remaining: 1.6s
165:	learn: 1.0410624	total: 191ms	remaining: 1.59s
166:	learn: 1.0392913	total: 193ms	remaining: 1.59s
167:	learn: 1.0372189	total: 194ms	remaining: 1.59s
168:	learn: 1.0356844	total: 195ms	remaining: 1.59s
169:	learn: 1.0339684	total: 196ms	remaining: 1.59s
170:	learn: 1.0322072	total: 197ms	remaining: 1.59s
171:	learn: 1.0306088	total: 198ms	remaining: 1.59s
172:	learn: 1.0289329	total: 200ms	remaining: 1.59s
173:	learn: 1.0273748	total: 201ms	remaining: 1.59s
174:	learn: 1.0261487	total: 202ms	remaining: 1.59s
175:	learn: 1.0248152	total: 204ms	remaining: 1.59s
176:	learn: 1.0232446	total: 205ms	remaining: 1.59s
177:	learn: 1.0218824	total: 206ms	remaining: 1.59s
178:	learn: 1.0199832	total: 207ms	remaining: 1.59s
179:	learn: 1.0183644	total: 208ms	remaining: 1.58s
180:	learn: 1.0169998	total: 209ms	remaining: 1.58s
181:	learn: 1.0154518	total: 211ms	remaining: 1.58s
182:	learn: 1.0141511	total: 212ms	remaining: 1.58s
183:	learn: 1.0130305	total: 213ms	remaining: 1.58s
184:	learn: 1.0117717	total: 214ms	remaining: 1.58s
185:	learn: 1.0102392	total: 215ms	remaining: 1.58s
186:	learn: 1.0090452	total: 216ms	remaining: 1.58s
187:	learn: 1.0077783	total: 218ms	remaining: 1.58s
188:	learn: 1.0066077	total: 219ms	remaining: 1.57s
189:	learn: 1.0054470	total: 220ms	remaining: 1.57s
190:	learn: 1.0037605	total: 221ms	remaining: 1.57s
191:	learn: 1.0025306	total: 223ms	remaining: 1.57s
192:	learn: 1.0012070	total: 224ms	remaining: 1.57s
193:	learn: 0.9999691	total: 225ms	remaining: 1.57s
194:	learn: 0.9983087	total: 226ms	remaining: 1.57s
195:	learn: 0.9969804	total: 227ms	remaining: 1.57s
196:	learn: 0.9956702	total: 228ms	remaining: 1.57s
197:	learn: 0.9945647	total: 230ms	remaining: 1.57s
198:	learn: 0.9932086	total: 231ms	remaining: 1.56s
199:	learn: 0.9921861	total: 232ms	remaining: 1.56s
200:	learn: 0.9908501	total: 233ms	remaining: 1.56s
201:	learn: 0.9896451	total: 234ms	remaining: 1.56s
202:	learn: 0.9883359	total: 235ms	remaining: 1.56s
203:	learn: 0.9871753	total: 237ms	remaining: 1.56s
204:	learn: 0.9858471	total: 238ms	remaining: 1.56s
205:	learn: 0.9847349	total: 239ms	remaining: 1.56s
206:	learn: 0.9837879	total: 240ms	remaining: 1.56s
207:	learn: 0.9826110	total: 242ms	remaining: 1.56s
208:	learn: 0.9816672	total: 243ms	remaining: 1.56s
209:	learn: 0.9805247	total: 244ms	remaining: 1.56s
210:	learn: 0.9792767	total: 245ms	remaining: 1.55s
211:	learn: 0.9781525	total: 246ms	remaining: 1.55s
212:	learn: 0.9769572	total: 247ms	remaining: 1.55s
213:	learn: 0.9757552	total: 249ms	remaining: 1.55s
214:	learn: 0.9746426	total: 250ms	remaining: 1.55s
215:	learn: 0.9737341	total: 251ms	remaining: 1.55s
216:	learn: 0.9727961	total: 252ms	remaining: 1.55s
217:	learn: 0.9717971	total: 253ms	remaining: 1.55s
218:	learn: 0.9702496	total: 254ms	remaining: 1.54s
219:	learn: 0.9691739	total: 256ms	remaining: 1.54s
220:	learn: 0.9683175	total: 257ms	remaining: 1.54s
221:	learn: 0.9670565	total: 258ms	remaining: 1.54s
222:	learn: 0.9657034	total: 259ms	remaining: 1.54s
223:	learn: 0.9645944	total: 260ms	remaining: 1.54s
224:	learn: 0.9634297	total: 261ms	remaining: 1.54s
225:	learn: 0.9622315	total: 262ms	remaining: 1.54s
226:	learn: 0.9611115	total: 263ms	remaining: 1.53s
227:	learn: 0.9600731	total: 265ms	remaining: 1.53s
228:	learn: 0.9593261	total: 266ms	remaining: 1.53s
229:	learn: 0.9585628	total: 267ms	remaining: 1.53s
230:	learn: 0.9573451	total: 268ms	remaining: 1.53s
231:	learn: 0.9563865	total: 269ms	remaining: 1.53s
232:	learn: 0.9555917	total: 270ms	remaining: 1.53s
233:	learn: 0.9546975	total: 271ms	remaining: 1.52s
234:	learn: 0.9536586	total: 272ms	remaining: 1.52s
235:	learn: 0.9528219	total: 274ms	remaining: 1.52s
236:	learn: 0.9516377	total: 275ms	remaining: 1.52s
237:	learn: 0.9503300	total: 276ms	remaining: 1.52s
238:	learn: 0.9491500	total: 277ms	remaining: 1.52s
239:	learn: 0.9481636	total: 278ms	remaining: 1.52s
240:	learn: 0.9472148	total: 280ms	remaining: 1.52s
241:	learn: 0.9462556	total: 281ms	remaining: 1.52s
242:	learn: 0.9454413	total: 282ms	remaining: 1.52s
243:	learn: 0.9447933	total: 283ms	remaining: 1.51s
244:	learn: 0.9436917	total: 284ms	remaining: 1.51s
245:	learn: 0.9429668	total: 285ms	remaining: 1.51s
246:	learn: 0.9422361	total: 286ms	remaining: 1.51s
247:	learn: 0.9412290	total: 287ms	remaining: 1.51s
248:	learn: 0.9404234	total: 289ms	remaining: 1.51s
249:	learn: 0.9393255	total: 290ms	remaining: 1.51s
250:	learn: 0.9383503	total: 291ms	remaining: 1.5s
251:	learn: 0.9375892	total: 292ms	remaining: 1.5s
252:	learn: 0.9365517	total: 293ms	remaining: 1.5s
253:	learn: 0.9354943	total: 294ms	remaining: 1.5s
254:	learn: 0.9346194	total: 295ms	remaining: 1.5s
255:	learn: 0.9336431	total: 297ms	remaining: 1.5s
256:	learn: 0.9328472	total: 298ms	remaining: 1.5s
257:	learn: 0.9321219	total: 299ms	remaining: 1.5s
258:	learn: 0.9313491	total: 300ms	remaining: 1.5s
259:	learn: 0.9306416	total: 301ms	remaining: 1.49s
260:	learn: 0.9298998	total: 302ms	remaining: 1.49s
261:	learn: 0.9291190	total: 303ms	remaining: 1.49s
262:	learn: 0.9284209	total: 305ms	remaining: 1.49s
263:	learn: 0.9278600	total: 306ms	remaining: 1.49s
264:	learn: 0.9266454	total: 307ms	remaining: 1.49s
265:	learn: 0.9255927	total: 308ms	remaining: 1.49s
266:	learn: 0.9250193	total: 309ms	remaining: 1.48s
267:	learn: 0.9240619	total: 310ms	remaining: 1.48s
268:	learn: 0.9231635	total: 311ms	remaining: 1.48s
269:	learn: 0.9222122	total: 313ms	remaining: 1.48s
270:	learn: 0.9216615	total: 314ms	remaining: 1.48s
271:	learn: 0.9208007	total: 315ms	remaining: 1.48s
272:	learn: 0.9199854	total: 316ms	remaining: 1.48s
273:	learn: 0.9190637	total: 317ms	remaining: 1.48s
274:	learn: 0.9184299	total: 318ms	remaining: 1.48s
275:	learn: 0.9178031	total: 319ms	remaining: 1.47s
276:	learn: 0.9171264	total: 320ms	remaining: 1.47s
277:	learn: 0.9165114	total: 322ms	remaining: 1.47s
278:	learn: 0.9156520	total: 323ms	remaining: 1.47s
279:	learn: 0.9147435	total: 324ms	remaining: 1.47s
280:	learn: 0.9142483	total: 325ms	remaining: 1.47s
281:	learn: 0.9134325	total: 326ms	remaining: 1.47s
282:	learn: 0.9129324	total: 327ms	remaining: 1.46s
283:	learn: 0.9120434	total: 328ms	remaining: 1.46s
284:	learn: 0.9113310	total: 329ms	remaining: 1.46s
285:	learn: 0.9107545	total: 330ms	remaining: 1.46s
286:	learn: 0.9104241	total: 331ms	remaining: 1.45s
287:	learn: 0.9095020	total: 332ms	remaining: 1.45s
288:	learn: 0.9086319	total: 333ms	remaining: 1.45s
289:	learn: 0.9078929	total: 334ms	remaining: 1.45s
290:	learn: 0.9071578	total: 335ms	remaining: 1.45s
291:	learn: 0.9066329	total: 336ms	remaining: 1.45s
292:	learn: 0.9059760	total: 337ms	remaining: 1.45s
293:	learn: 0.9054925	total: 339ms	remaining: 1.45s
294:	learn: 0.9049571	total: 340ms	remaining: 1.44s
295:	learn: 0.9041056	total: 341ms	remaining: 1.44s
296:	learn: 0.9035044	total: 342ms	remaining: 1.44s
297:	learn: 0.9029845	total: 343ms	remaining: 1.44s
298:	learn: 0.9024139	total: 344ms	remaining: 1.44s
299:	learn: 0.9018041	total: 345ms	remaining: 1.44s
300:	learn: 0.9008530	total: 346ms	remaining: 1.44s
301:	learn: 0.8999381	total: 347ms	remaining: 1.44s
302:	learn: 0.8992668	total: 348ms	remaining: 1.43s
303:	learn: 0.8985313	total: 350ms	remaining: 1.43s
304:	learn: 0.8979551	total: 351ms	remaining: 1.43s
305:	learn: 0.8973199	total: 352ms	remaining: 1.43s
306:	learn: 0.8965369	total: 353ms	remaining: 1.43s
307:	learn: 0.8959292	total: 354ms	remaining: 1.43s
308:	learn: 0.8950656	total: 355ms	remaining: 1.43s
309:	learn: 0.8945438	total: 356ms	remaining: 1.43s
310:	learn: 0.8937944	total: 358ms	remaining: 1.42s
311:	learn: 0.8930149	total: 359ms	remaining: 1.42s
312:	learn: 0.8925040	total: 360ms	remaining: 1.42s
313:	learn: 0.8919235	total: 361ms	remaining: 1.42s
314:	learn: 0.8912195	total: 362ms	remaining: 1.42s
315:	learn: 0.8906839	total: 363ms	remaining: 1.42s
316:	learn: 0.8901516	total: 365ms	remaining: 1.42s
317:	learn: 0.8893619	total: 366ms	remaining: 1.42s
318:	learn: 0.8886049	total: 367ms	remaining: 1.42s
319:	learn: 0.8877568	total: 368ms	remaining: 1.41s
320:	learn: 0.8869515	total: 369ms	remaining: 1.41s
321:	learn: 0.8862059	total: 370ms	remaining: 1.41s
322:	learn: 0.8856021	total: 372ms	remaining: 1.41s
323:	learn: 0.8848398	total: 373ms	remaining: 1.41s
324:	learn: 0.8843230	total: 374ms	remaining: 1.41s
325:	learn: 0.8838954	total: 375ms	remaining: 1.41s
326:	learn: 0.8834542	total: 376ms	remaining: 1.41s
327:	learn: 0.8830228	total: 377ms	remaining: 1.41s
328:	learn: 0.8823671	total: 378ms	remaining: 1.4s
329:	learn: 0.8816522	total: 380ms	remaining: 1.4s
330:	learn: 0.8809206	total: 381ms	remaining: 1.4s
331:	learn: 0.8802093	total: 382ms	remaining: 1.4s
332:	learn: 0.8796508	total: 383ms	remaining: 1.4s
333:	learn: 0.8789204	total: 384ms	remaining: 1.4s
334:	learn: 0.8780841	total: 385ms	remaining: 1.4s
335:	learn: 0.8775077	total: 386ms	remaining: 1.4s
336:	learn: 0.8768246	total: 388ms	remaining: 1.4s
337:	learn: 0.8761715	total: 389ms	remaining: 1.39s
338:	learn: 0.8756205	total: 390ms	remaining: 1.39s
339:	learn: 0.8751132	total: 391ms	remaining: 1.39s
340:	learn: 0.8744548	total: 392ms	remaining: 1.39s
341:	learn: 0.8737748	total: 394ms	remaining: 1.39s
342:	learn: 0.8732215	total: 395ms	remaining: 1.39s
343:	learn: 0.8727634	total: 396ms	remaining: 1.39s
344:	learn: 0.8722560	total: 398ms	remaining: 1.39s
345:	learn: 0.8715320	total: 399ms	remaining: 1.39s
346:	learn: 0.8712104	total: 400ms	remaining: 1.39s
347:	learn: 0.8707878	total: 401ms	remaining: 1.39s
348:	learn: 0.8702692	total: 402ms	remaining: 1.38s
349:	learn: 0.8697649	total: 403ms	remaining: 1.38s
350:	learn: 0.8690631	total: 405ms	remaining: 1.38s
351:	learn: 0.8686668	total: 406ms	remaining: 1.38s
352:	learn: 0.8680699	total: 407ms	remaining: 1.38s
353:	learn: 0.8674699	total: 408ms	remaining: 1.38s
354:	learn: 0.8672604	total: 409ms	remaining: 1.38s
355:	learn: 0.8664660	total: 410ms	remaining: 1.38s
356:	learn: 0.8660828	total: 412ms	remaining: 1.38s
357:	learn: 0.8657115	total: 413ms	remaining: 1.38s
358:	learn: 0.8654315	total: 414ms	remaining: 1.37s
359:	learn: 0.8650597	total: 416ms	remaining: 1.37s
360:	learn: 0.8642991	total: 417ms	remaining: 1.37s
361:	learn: 0.8638498	total: 418ms	remaining: 1.37s
362:	learn: 0.8632593	total: 420ms	remaining: 1.37s
363:	learn: 0.8628860	total: 421ms	remaining: 1.37s
364:	learn: 0.8622472	total: 422ms	remaining: 1.37s
365:	learn: 0.8618630	total: 423ms	remaining: 1.37s
366:	learn: 0.8613032	total: 425ms	remaining: 1.37s
367:	learn: 0.8607889	total: 426ms	remaining: 1.37s
368:	learn: 0.8604329	total: 427ms	remaining: 1.37s
369:	learn: 0.8599578	total: 428ms	remaining: 1.37s
370:	learn: 0.8593278	total: 430ms	remaining: 1.36s
371:	learn: 0.8585466	total: 431ms	remaining: 1.36s
372:	learn: 0.8583079	total: 432ms	remaining: 1.36s
373:	learn: 0.8577969	total: 433ms	remaining: 1.36s
374:	learn: 0.8574704	total: 434ms	remaining: 1.36s
375:	learn: 0.8569072	total: 435ms	remaining: 1.36s
376:	learn: 0.8564058	total: 437ms	remaining: 1.36s
377:	learn: 0.8560349	total: 438ms	remaining: 1.36s
378:	learn: 0.8556605	total: 439ms	remaining: 1.36s
379:	learn: 0.8553066	total: 440ms	remaining: 1.35s
380:	learn: 0.8550186	total: 441ms	remaining: 1.35s
381:	learn: 0.8544065	total: 443ms	remaining: 1.35s
382:	learn: 0.8539237	total: 444ms	remaining: 1.35s
383:	learn: 0.8533444	total: 445ms	remaining: 1.35s
384:	learn: 0.8529835	total: 446ms	remaining: 1.35s
385:	learn: 0.8522770	total: 448ms	remaining: 1.35s
386:	learn: 0.8515457	total: 449ms	remaining: 1.35s
387:	learn: 0.8510764	total: 450ms	remaining: 1.35s
388:	learn: 0.8505106	total: 451ms	remaining: 1.35s
389:	learn: 0.8501421	total: 453ms	remaining: 1.35s
390:	learn: 0.8497838	total: 454ms	remaining: 1.34s
391:	learn: 0.8494291	total: 455ms	remaining: 1.34s
392:	learn: 0.8489375	total: 456ms	remaining: 1.34s
393:	learn: 0.8484874	total: 457ms	remaining: 1.34s
394:	learn: 0.8483506	total: 458ms	remaining: 1.34s
395:	learn: 0.8477093	total: 459ms	remaining: 1.34s
396:	learn: 0.8467909	total: 460ms	remaining: 1.34s
397:	learn: 0.8464061	total: 461ms	remaining: 1.33s
398:	learn: 0.8458415	total: 463ms	remaining: 1.33s
399:	learn: 0.8453179	total: 464ms	remaining: 1.33s
400:	learn: 0.8449137	total: 465ms	remaining: 1.33s
401:	learn: 0.8445200	total: 466ms	remaining: 1.33s
402:	learn: 0.8441263	total: 468ms	remaining: 1.33s
403:	learn: 0.8435537	total: 469ms	remaining: 1.33s
404:	learn: 0.8429192	total: 470ms	remaining: 1.33s
405:	learn: 0.8426062	total: 471ms	remaining: 1.33s
406:	learn: 0.8423813	total: 473ms	remaining: 1.33s
407:	learn: 0.8419553	total: 474ms	remaining: 1.33s
408:	learn: 0.8414441	total: 475ms	remaining: 1.32s
409:	learn: 0.8409848	total: 477ms	remaining: 1.32s
410:	learn: 0.8406892	total: 477ms	remaining: 1.32s
411:	learn: 0.8403637	total: 478ms	remaining: 1.32s
412:	learn: 0.8400480	total: 479ms	remaining: 1.32s
413:	learn: 0.8396979	total: 481ms	remaining: 1.32s
414:	learn: 0.8392430	total: 482ms	remaining: 1.32s
415:	learn: 0.8388356	total: 483ms	remaining: 1.32s
416:	learn: 0.8384545	total: 484ms	remaining: 1.31s
417:	learn: 0.8380817	total: 485ms	remaining: 1.31s
418:	learn: 0.8377684	total: 487ms	remaining: 1.31s
419:	learn: 0.8375227	total: 488ms	remaining: 1.31s
420:	learn: 0.8370076	total: 489ms	remaining: 1.31s
421:	learn: 0.8364988	total: 490ms	remaining: 1.31s
422:	learn: 0.8360297	total: 492ms	remaining: 1.31s
423:	learn: 0.8356760	total: 493ms	remaining: 1.31s
424:	learn: 0.8354459	total: 494ms	remaining: 1.31s
425:	learn: 0.8349963	total: 495ms	remaining: 1.31s
426:	learn: 0.8343191	total: 497ms	remaining: 1.31s
427:	learn: 0.8339666	total: 498ms	remaining: 1.3s
428:	learn: 0.8333196	total: 499ms	remaining: 1.3s
429:	learn: 0.8332669	total: 500ms	remaining: 1.3s
430:	learn: 0.8327172	total: 501ms	remaining: 1.3s
431:	learn: 0.8321332	total: 502ms	remaining: 1.3s
432:	learn: 0.8318818	total: 504ms	remaining: 1.3s
433:	learn: 0.8314618	total: 505ms	remaining: 1.3s
434:	learn: 0.8309364	total: 506ms	remaining: 1.3s
435:	learn: 0.8306831	total: 507ms	remaining: 1.3s
436:	learn: 0.8299701	total: 509ms	remaining: 1.29s
437:	learn: 0.8294460	total: 510ms	remaining: 1.29s
438:	learn: 0.8290151	total: 511ms	remaining: 1.29s
439:	learn: 0.8285768	total: 512ms	remaining: 1.29s
440:	learn: 0.8280367	total: 513ms	remaining: 1.29s
441:	learn: 0.8275668	total: 515ms	remaining: 1.29s
442:	learn: 0.8273620	total: 516ms	remaining: 1.29s
443:	learn: 0.8270481	total: 517ms	remaining: 1.29s
444:	learn: 0.8266350	total: 518ms	remaining: 1.29s
445:	learn: 0.8260582	total: 520ms	remaining: 1.29s
446:	learn: 0.8255775	total: 521ms	remaining: 1.28s
447:	learn: 0.8249022	total: 522ms	remaining: 1.28s
448:	learn: 0.8244740	total: 524ms	remaining: 1.28s
449:	learn: 0.8241346	total: 525ms	remaining: 1.28s
450:	learn: 0.8238531	total: 526ms	remaining: 1.28s
451:	learn: 0.8234726	total: 527ms	remaining: 1.28s
452:	learn: 0.8231191	total: 528ms	remaining: 1.28s
453:	learn: 0.8226977	total: 530ms	remaining: 1.28s
454:	learn: 0.8224258	total: 531ms	remaining: 1.28s
455:	learn: 0.8220966	total: 532ms	remaining: 1.28s
456:	learn: 0.8215961	total: 533ms	remaining: 1.27s
457:	learn: 0.8212321	total: 535ms	remaining: 1.27s
458:	learn: 0.8208534	total: 536ms	remaining: 1.27s
459:	learn: 0.8203065	total: 537ms	remaining: 1.27s
460:	learn: 0.8197862	total: 538ms	remaining: 1.27s
461:	learn: 0.8193642	total: 540ms	remaining: 1.27s
462:	learn: 0.8192039	total: 541ms	remaining: 1.27s
463:	learn: 0.8188531	total: 542ms	remaining: 1.27s
464:	learn: 0.8184420	total: 544ms	remaining: 1.27s
465:	learn: 0.8180964	total: 545ms	remaining: 1.27s
466:	learn: 0.8177779	total: 546ms	remaining: 1.27s
467:	learn: 0.8172782	total: 547ms	remaining: 1.26s
468:	learn: 0.8169581	total: 549ms	remaining: 1.26s
469:	learn: 0.8166177	total: 550ms	remaining: 1.26s
470:	learn: 0.8161764	total: 551ms	remaining: 1.26s
471:	learn: 0.8158880	total: 552ms	remaining: 1.26s
472:	learn: 0.8155297	total: 554ms	remaining: 1.26s
473:	learn: 0.8151910	total: 555ms	remaining: 1.26s
474:	learn: 0.8149433	total: 556ms	remaining: 1.26s
475:	learn: 0.8143607	total: 557ms	remaining: 1.26s
476:	learn: 0.8139635	total: 558ms	remaining: 1.26s
477:	learn: 0.8136936	total: 560ms	remaining: 1.25s
478:	learn: 0.8134232	total: 561ms	remaining: 1.25s
479:	learn: 0.8130214	total: 562ms	remaining: 1.25s
480:	learn: 0.8126827	total: 563ms	remaining: 1.25s
481:	learn: 0.8123179	total: 564ms	remaining: 1.25s
482:	learn: 0.8120956	total: 565ms	remaining: 1.25s
483:	learn: 0.8115867	total: 567ms	remaining: 1.25s
484:	learn: 0.8111630	total: 568ms	remaining: 1.25s
485:	learn: 0.8107533	total: 569ms	remaining: 1.25s
486:	learn: 0.8103283	total: 570ms	remaining: 1.24s
487:	learn: 0.8100223	total: 571ms	remaining: 1.24s
488:	learn: 0.8096149	total: 572ms	remaining: 1.24s
489:	learn: 0.8093921	total: 573ms	remaining: 1.24s
490:	learn: 0.8091225	total: 574ms	remaining: 1.24s
491:	learn: 0.8088082	total: 575ms	remaining: 1.24s
492:	learn: 0.8082448	total: 577ms	remaining: 1.24s
493:	learn: 0.8078853	total: 578ms	remaining: 1.23s
494:	learn: 0.8075215	total: 579ms	remaining: 1.23s
495:	learn: 0.8073222	total: 580ms	remaining: 1.23s
496:	learn: 0.8068660	total: 581ms	remaining: 1.23s
497:	learn: 0.8064661	total: 582ms	remaining: 1.23s
498:	learn: 0.8059751	total: 583ms	remaining: 1.23s
499:	learn: 0.8059319	total: 584ms	remaining: 1.23s
500:	learn: 0.8056171	total: 585ms	remaining: 1.22s
501:	learn: 0.8052136	total: 586ms	remaining: 1.22s
502:	learn: 0.8048523	total: 587ms	remaining: 1.22s
503:	learn: 0.8044533	total: 588ms	remaining: 1.22s
504:	learn: 0.8042007	total: 589ms	remaining: 1.22s
505:	learn: 0.8038968	total: 591ms	remaining: 1.22s
506:	learn: 0.8035288	total: 592ms	remaining: 1.22s
507:	learn: 0.8033955	total: 594ms	remaining: 1.22s
508:	learn: 0.8027654	total: 595ms	remaining: 1.22s
509:	learn: 0.8025084	total: 596ms	remaining: 1.22s
510:	learn: 0.8021109	total: 597ms	remaining: 1.21s
511:	learn: 0.8017314	total: 598ms	remaining: 1.21s
512:	learn: 0.8014840	total: 600ms	remaining: 1.21s
513:	learn: 0.8011743	total: 601ms	remaining: 1.21s
514:	learn: 0.8008536	total: 602ms	remaining: 1.21s
515:	learn: 0.8005819	total: 603ms	remaining: 1.21s
516:	learn: 0.7997868	total: 604ms	remaining: 1.21s
517:	learn: 0.7993309	total: 606ms	remaining: 1.21s
518:	learn: 0.7990260	total: 607ms	remaining: 1.21s
519:	learn: 0.7986517	total: 608ms	remaining: 1.2s
520:	learn: 0.7982762	total: 609ms	remaining: 1.2s
521:	learn: 0.7976987	total: 610ms	remaining: 1.2s
522:	learn: 0.7973507	total: 612ms	remaining: 1.2s
523:	learn: 0.7969088	total: 613ms	remaining: 1.2s
524:	learn: 0.7965591	total: 614ms	remaining: 1.2s
525:	learn: 0.7963471	total: 615ms	remaining: 1.2s
526:	learn: 0.7958560	total: 616ms	remaining: 1.2s
527:	learn: 0.7955894	total: 618ms	remaining: 1.2s
528:	learn: 0.7953748	total: 619ms	remaining: 1.19s
529:	learn: 0.7948968	total: 620ms	remaining: 1.19s
530:	learn: 0.7945411	total: 621ms	remaining: 1.19s
531:	learn: 0.7942299	total: 622ms	remaining: 1.19s
532:	learn: 0.7939864	total: 623ms	remaining: 1.19s
533:	learn: 0.7937188	total: 624ms	remaining: 1.19s
534:	learn: 0.7932860	total: 626ms	remaining: 1.19s
535:	learn: 0.7929614	total: 627ms	remaining: 1.19s
536:	learn: 0.7927753	total: 628ms	remaining: 1.18s
537:	learn: 0.7924639	total: 629ms	remaining: 1.18s
538:	learn: 0.7921033	total: 630ms	remaining: 1.18s
539:	learn: 0.7916846	total: 631ms	remaining: 1.18s
540:	learn: 0.7912827	total: 632ms	remaining: 1.18s
541:	learn: 0.7910249	total: 633ms	remaining: 1.18s
542:	learn: 0.7907329	total: 634ms	remaining: 1.18s
543:	learn: 0.7905327	total: 636ms	remaining: 1.18s
544:	learn: 0.7902438	total: 637ms	remaining: 1.17s
545:	learn: 0.7898308	total: 638ms	remaining: 1.17s
546:	learn: 0.7896363	total: 639ms	remaining: 1.17s
547:	learn: 0.7893828	total: 640ms	remaining: 1.17s
548:	learn: 0.7891842	total: 641ms	remaining: 1.17s
549:	learn: 0.7889612	total: 642ms	remaining: 1.17s
550:	learn: 0.7885908	total: 644ms	remaining: 1.17s
551:	learn: 0.7883884	total: 645ms	remaining: 1.17s
552:	learn: 0.7879752	total: 646ms	remaining: 1.16s
553:	learn: 0.7877480	total: 647ms	remaining: 1.16s
554:	learn: 0.7875166	total: 648ms	remaining: 1.16s
555:	learn: 0.7873099	total: 649ms	remaining: 1.16s
556:	learn: 0.7870882	total: 650ms	remaining: 1.16s
557:	learn: 0.7867567	total: 651ms	remaining: 1.16s
558:	learn: 0.7863910	total: 653ms	remaining: 1.16s
559:	learn: 0.7861447	total: 654ms	remaining: 1.16s
560:	learn: 0.7855646	total: 655ms	remaining: 1.16s
561:	learn: 0.7849985	total: 656ms	remaining: 1.15s
562:	learn: 0.7847251	total: 658ms	remaining: 1.15s
563:	learn: 0.7844135	total: 659ms	remaining: 1.15s
564:	learn: 0.7841813	total: 660ms	remaining: 1.15s
565:	learn: 0.7838748	total: 661ms	remaining: 1.15s
566:	learn: 0.7834478	total: 662ms	remaining: 1.15s
567:	learn: 0.7832880	total: 664ms	remaining: 1.15s
568:	learn: 0.7831292	total: 665ms	remaining: 1.15s
569:	learn: 0.7829289	total: 666ms	remaining: 1.14s
570:	learn: 0.7825660	total: 667ms	remaining: 1.14s
571:	learn: 0.7821480	total: 668ms	remaining: 1.14s
572:	learn: 0.7818999	total: 669ms	remaining: 1.14s
573:	learn: 0.7815768	total: 670ms	remaining: 1.14s
574:	learn: 0.7813939	total: 671ms	remaining: 1.14s
575:	learn: 0.7810089	total: 673ms	remaining: 1.14s
576:	learn: 0.7804902	total: 674ms	remaining: 1.14s
577:	learn: 0.7801679	total: 675ms	remaining: 1.13s
578:	learn: 0.7800053	total: 676ms	remaining: 1.13s
579:	learn: 0.7796209	total: 677ms	remaining: 1.13s
580:	learn: 0.7794374	total: 678ms	remaining: 1.13s
581:	learn: 0.7791339	total: 679ms	remaining: 1.13s
582:	learn: 0.7788424	total: 681ms	remaining: 1.13s
583:	learn: 0.7785751	total: 682ms	remaining: 1.13s
584:	learn: 0.7781992	total: 683ms	remaining: 1.13s
585:	learn: 0.7780553	total: 684ms	remaining: 1.13s
586:	learn: 0.7776779	total: 685ms	remaining: 1.12s
587:	learn: 0.7774018	total: 686ms	remaining: 1.12s
588:	learn: 0.7771601	total: 687ms	remaining: 1.12s
589:	learn: 0.7768619	total: 688ms	remaining: 1.12s
590:	learn: 0.7765177	total: 690ms	remaining: 1.12s
591:	learn: 0.7762082	total: 691ms	remaining: 1.12s
592:	learn: 0.7757815	total: 692ms	remaining: 1.12s
593:	learn: 0.7756641	total: 693ms	remaining: 1.11s
594:	learn: 0.7751458	total: 694ms	remaining: 1.11s
595:	learn: 0.7748352	total: 695ms	remaining: 1.11s
596:	learn: 0.7746032	total: 696ms	remaining: 1.11s
597:	learn: 0.7741223	total: 697ms	remaining: 1.11s
598:	learn: 0.7739818	total: 699ms	remaining: 1.11s
599:	learn: 0.7736634	total: 700ms	remaining: 1.11s
600:	learn: 0.7733507	total: 701ms	remaining: 1.11s
601:	learn: 0.7729904	total: 702ms	remaining: 1.1s
602:	learn: 0.7725872	total: 703ms	remaining: 1.1s
603:	learn: 0.7722518	total: 704ms	remaining: 1.1s
604:	learn: 0.7720254	total: 705ms	remaining: 1.1s
605:	learn: 0.7716394	total: 706ms	remaining: 1.1s
606:	learn: 0.7715373	total: 707ms	remaining: 1.1s
607:	learn: 0.7712897	total: 709ms	remaining: 1.1s
608:	learn: 0.7707960	total: 710ms	remaining: 1.1s
609:	learn: 0.7704834	total: 711ms	remaining: 1.09s
610:	learn: 0.7701788	total: 712ms	remaining: 1.09s
611:	learn: 0.7699173	total: 713ms	remaining: 1.09s
612:	learn: 0.7695498	total: 714ms	remaining: 1.09s
613:	learn: 0.7691873	total: 715ms	remaining: 1.09s
614:	learn: 0.7687253	total: 716ms	remaining: 1.09s
615:	learn: 0.7683859	total: 718ms	remaining: 1.09s
616:	learn: 0.7682470	total: 719ms	remaining: 1.09s
617:	learn: 0.7680720	total: 720ms	remaining: 1.08s
618:	learn: 0.7678122	total: 721ms	remaining: 1.08s
619:	learn: 0.7673786	total: 722ms	remaining: 1.08s
620:	learn: 0.7671969	total: 723ms	remaining: 1.08s
621:	learn: 0.7669787	total: 724ms	remaining: 1.08s
622:	learn: 0.7669321	total: 725ms	remaining: 1.08s
623:	learn: 0.7666755	total: 726ms	remaining: 1.08s
624:	learn: 0.7664770	total: 727ms	remaining: 1.07s
625:	learn: 0.7662678	total: 728ms	remaining: 1.07s
626:	learn: 0.7661789	total: 729ms	remaining: 1.07s
627:	learn: 0.7658259	total: 730ms	remaining: 1.07s
628:	learn: 0.7656722	total: 732ms	remaining: 1.07s
629:	learn: 0.7655101	total: 733ms	remaining: 1.07s
630:	learn: 0.7650089	total: 734ms	remaining: 1.07s
631:	learn: 0.7648108	total: 735ms	remaining: 1.07s
632:	learn: 0.7645848	total: 736ms	remaining: 1.07s
633:	learn: 0.7642697	total: 737ms	remaining: 1.06s
634:	learn: 0.7639776	total: 738ms	remaining: 1.06s
635:	learn: 0.7636112	total: 739ms	remaining: 1.06s
636:	learn: 0.7632191	total: 741ms	remaining: 1.06s
637:	learn: 0.7629516	total: 742ms	remaining: 1.06s
638:	learn: 0.7626577	total: 743ms	remaining: 1.06s
639:	learn: 0.7621584	total: 744ms	remaining: 1.06s
640:	learn: 0.7616696	total: 745ms	remaining: 1.06s
641:	learn: 0.7612835	total: 746ms	remaining: 1.05s
642:	learn: 0.7611319	total: 747ms	remaining: 1.05s
643:	learn: 0.7609557	total: 748ms	remaining: 1.05s
644:	learn: 0.7607129	total: 749ms	remaining: 1.05s
645:	learn: 0.7604805	total: 751ms	remaining: 1.05s
646:	learn: 0.7602755	total: 752ms	remaining: 1.05s
647:	learn: 0.7599457	total: 753ms	remaining: 1.05s
648:	learn: 0.7595569	total: 754ms	remaining: 1.05s
649:	learn: 0.7592136	total: 755ms	remaining: 1.04s
650:	learn: 0.7590409	total: 756ms	remaining: 1.04s
651:	learn: 0.7588265	total: 758ms	remaining: 1.04s
652:	learn: 0.7586665	total: 759ms	remaining: 1.04s
653:	learn: 0.7583914	total: 760ms	remaining: 1.04s
654:	learn: 0.7579637	total: 761ms	remaining: 1.04s
655:	learn: 0.7576782	total: 763ms	remaining: 1.04s
656:	learn: 0.7575472	total: 764ms	remaining: 1.04s
657:	learn: 0.7572764	total: 765ms	remaining: 1.04s
658:	learn: 0.7569428	total: 766ms	remaining: 1.03s
659:	learn: 0.7566282	total: 767ms	remaining: 1.03s
660:	learn: 0.7562716	total: 768ms	remaining: 1.03s
661:	learn: 0.7560402	total: 770ms	remaining: 1.03s
662:	learn: 0.7557267	total: 771ms	remaining: 1.03s
663:	learn: 0.7556207	total: 772ms	remaining: 1.03s
664:	learn: 0.7553464	total: 773ms	remaining: 1.03s
665:	learn: 0.7551619	total: 774ms	remaining: 1.03s
666:	learn: 0.7549420	total: 775ms	remaining: 1.03s
667:	learn: 0.7547872	total: 776ms	remaining: 1.02s
668:	learn: 0.7544713	total: 777ms	remaining: 1.02s
669:	learn: 0.7542489	total: 779ms	remaining: 1.02s
670:	learn: 0.7540349	total: 780ms	remaining: 1.02s
671:	learn: 0.7536396	total: 781ms	remaining: 1.02s
672:	learn: 0.7532805	total: 782ms	remaining: 1.02s
673:	learn: 0.7529615	total: 783ms	remaining: 1.02s
674:	learn: 0.7527119	total: 784ms	remaining: 1.02s
675:	learn: 0.7522823	total: 785ms	remaining: 1.01s
676:	learn: 0.7519250	total: 787ms	remaining: 1.01s
677:	learn: 0.7518189	total: 788ms	remaining: 1.01s
678:	learn: 0.7515378	total: 789ms	remaining: 1.01s
679:	learn: 0.7510354	total: 790ms	remaining: 1.01s
680:	learn: 0.7507171	total: 791ms	remaining: 1.01s
681:	learn: 0.7505428	total: 793ms	remaining: 1.01s
682:	learn: 0.7503330	total: 794ms	remaining: 1.01s
683:	learn: 0.7499223	total: 795ms	remaining: 1.01s
684:	learn: 0.7495665	total: 796ms	remaining: 1s
685:	learn: 0.7491081	total: 797ms	remaining: 1s
686:	learn: 0.7487937	total: 798ms	remaining: 1s
687:	learn: 0.7486643	total: 800ms	remaining: 1s
688:	learn: 0.7483079	total: 801ms	remaining: 1s
689:	learn: 0.7481331	total: 802ms	remaining: 1000ms
690:	learn: 0.7477401	total: 803ms	remaining: 999ms
691:	learn: 0.7476082	total: 805ms	remaining: 998ms
692:	learn: 0.7472839	total: 806ms	remaining: 997ms
693:	learn: 0.7469688	total: 807ms	remaining: 995ms
694:	learn: 0.7466537	total: 808ms	remaining: 994ms
695:	learn: 0.7464247	total: 809ms	remaining: 993ms
696:	learn: 0.7461469	total: 810ms	remaining: 992ms
697:	learn: 0.7457912	total: 812ms	remaining: 991ms
698:	learn: 0.7454572	total: 813ms	remaining: 990ms
699:	learn: 0.7451157	total: 814ms	remaining: 989ms
700:	learn: 0.7447850	total: 815ms	remaining: 987ms
701:	learn: 0.7445707	total: 816ms	remaining: 986ms
702:	learn: 0.7443768	total: 817ms	remaining: 985ms
703:	learn: 0.7442433	total: 819ms	remaining: 984ms
704:	learn: 0.7440571	total: 820ms	remaining: 982ms
705:	learn: 0.7437074	total: 821ms	remaining: 981ms
706:	learn: 0.7433813	total: 822ms	remaining: 980ms
707:	learn: 0.7431335	total: 823ms	remaining: 979ms
708:	learn: 0.7430325	total: 824ms	remaining: 978ms
709:	learn: 0.7427904	total: 825ms	remaining: 976ms
710:	learn: 0.7424646	total: 826ms	remaining: 975ms
711:	learn: 0.7422824	total: 828ms	remaining: 974ms
712:	learn: 0.7420109	total: 829ms	remaining: 973ms
713:	learn: 0.7416897	total: 830ms	remaining: 972ms
714:	learn: 0.7415669	total: 831ms	remaining: 971ms
715:	learn: 0.7412678	total: 832ms	remaining: 969ms
716:	learn: 0.7409213	total: 833ms	remaining: 968ms
717:	learn: 0.7404349	total: 834ms	remaining: 967ms
718:	learn: 0.7399589	total: 836ms	remaining: 966ms
719:	learn: 0.7396977	total: 837ms	remaining: 964ms
720:	learn: 0.7395012	total: 838ms	remaining: 963ms
721:	learn: 0.7392572	total: 839ms	remaining: 962ms
722:	learn: 0.7389536	total: 840ms	remaining: 961ms
723:	learn: 0.7387378	total: 841ms	remaining: 960ms
724:	learn: 0.7384166	total: 842ms	remaining: 958ms
725:	learn: 0.7380603	total: 843ms	remaining: 957ms
726:	learn: 0.7376649	total: 845ms	remaining: 956ms
727:	learn: 0.7373810	total: 846ms	remaining: 955ms
728:	learn: 0.7371899	total: 847ms	remaining: 954ms
729:	learn: 0.7369469	total: 848ms	remaining: 952ms
730:	learn: 0.7367262	total: 849ms	remaining: 951ms
731:	learn: 0.7362042	total: 850ms	remaining: 950ms
732:	learn: 0.7359947	total: 851ms	remaining: 949ms
733:	learn: 0.7357591	total: 852ms	remaining: 948ms
734:	learn: 0.7354745	total: 854ms	remaining: 947ms
735:	learn: 0.7352277	total: 855ms	remaining: 945ms
736:	learn: 0.7349698	total: 856ms	remaining: 944ms
737:	learn: 0.7346791	total: 857ms	remaining: 943ms
738:	learn: 0.7345011	total: 858ms	remaining: 942ms
739:	learn: 0.7343289	total: 859ms	remaining: 941ms
740:	learn: 0.7340670	total: 861ms	remaining: 940ms
741:	learn: 0.7335078	total: 862ms	remaining: 938ms
742:	learn: 0.7331141	total: 863ms	remaining: 937ms
743:	learn: 0.7327645	total: 864ms	remaining: 936ms
744:	learn: 0.7324671	total: 865ms	remaining: 935ms
745:	learn: 0.7323152	total: 866ms	remaining: 934ms
746:	learn: 0.7320268	total: 867ms	remaining: 932ms
747:	learn: 0.7318038	total: 869ms	remaining: 931ms
748:	learn: 0.7315737	total: 870ms	remaining: 930ms
749:	learn: 0.7310365	total: 871ms	remaining: 929ms
750:	learn: 0.7309022	total: 872ms	remaining: 928ms
751:	learn: 0.7307625	total: 873ms	remaining: 927ms
752:	learn: 0.7304082	total: 875ms	remaining: 926ms
753:	learn: 0.7302470	total: 876ms	remaining: 924ms
754:	learn: 0.7299796	total: 877ms	remaining: 923ms
755:	learn: 0.7298933	total: 878ms	remaining: 922ms
756:	learn: 0.7297885	total: 879ms	remaining: 920ms
757:	learn: 0.7296631	total: 880ms	remaining: 919ms
758:	learn: 0.7295797	total: 881ms	remaining: 918ms
759:	learn: 0.7291240	total: 882ms	remaining: 917ms
760:	learn: 0.7287730	total: 883ms	remaining: 916ms
761:	learn: 0.7285188	total: 885ms	remaining: 915ms
762:	learn: 0.7283784	total: 886ms	remaining: 914ms
763:	learn: 0.7280973	total: 887ms	remaining: 912ms
764:	learn: 0.7278088	total: 888ms	remaining: 911ms
765:	learn: 0.7275214	total: 889ms	remaining: 910ms
766:	learn: 0.7273090	total: 891ms	remaining: 909ms
767:	learn: 0.7271534	total: 892ms	remaining: 908ms
768:	learn: 0.7268655	total: 893ms	remaining: 907ms
769:	learn: 0.7267464	total: 894ms	remaining: 906ms
770:	learn: 0.7264831	total: 896ms	remaining: 905ms
771:	learn: 0.7262860	total: 897ms	remaining: 904ms
772:	learn: 0.7260050	total: 898ms	remaining: 903ms
773:	learn: 0.7257776	total: 899ms	remaining: 902ms
774:	learn: 0.7255369	total: 900ms	remaining: 900ms
775:	learn: 0.7254070	total: 902ms	remaining: 899ms
776:	learn: 0.7251409	total: 903ms	remaining: 898ms
777:	learn: 0.7249892	total: 904ms	remaining: 897ms
778:	learn: 0.7248064	total: 905ms	remaining: 896ms
779:	learn: 0.7244606	total: 907ms	remaining: 895ms
780:	learn: 0.7241989	total: 908ms	remaining: 894ms
781:	learn: 0.7239355	total: 909ms	remaining: 893ms
782:	learn: 0.7237204	total: 911ms	remaining: 892ms
783:	learn: 0.7234746	total: 912ms	remaining: 891ms
784:	learn: 0.7232872	total: 913ms	remaining: 890ms
785:	learn: 0.7231960	total: 914ms	remaining: 889ms
786:	learn: 0.7229863	total: 916ms	remaining: 888ms
787:	learn: 0.7227937	total: 917ms	remaining: 887ms
788:	learn: 0.7223715	total: 918ms	remaining: 886ms
789:	learn: 0.7221828	total: 920ms	remaining: 885ms
790:	learn: 0.7217802	total: 921ms	remaining: 884ms
791:	learn: 0.7216379	total: 922ms	remaining: 883ms
792:	learn: 0.7214129	total: 924ms	remaining: 882ms
793:	learn: 0.7212130	total: 925ms	remaining: 881ms
794:	learn: 0.7208753	total: 926ms	remaining: 880ms
795:	learn: 0.7207012	total: 927ms	remaining: 879ms
796:	learn: 0.7205358	total: 929ms	remaining: 877ms
797:	learn: 0.7203292	total: 930ms	remaining: 876ms
798:	learn: 0.7202196	total: 931ms	remaining: 875ms
799:	learn: 0.7200934	total: 933ms	remaining: 874ms
800:	learn: 0.7199160	total: 934ms	remaining: 873ms
801:	learn: 0.7196296	total: 935ms	remaining: 872ms
802:	learn: 0.7192941	total: 937ms	remaining: 871ms
803:	learn: 0.7191336	total: 938ms	remaining: 870ms
804:	learn: 0.7189440	total: 939ms	remaining: 869ms
805:	learn: 0.7188320	total: 941ms	remaining: 868ms
806:	learn: 0.7186206	total: 942ms	remaining: 867ms
807:	learn: 0.7184885	total: 943ms	remaining: 866ms
808:	learn: 0.7182171	total: 944ms	remaining: 865ms
809:	learn: 0.7179792	total: 946ms	remaining: 864ms
810:	learn: 0.7177411	total: 947ms	remaining: 863ms
811:	learn: 0.7176067	total: 948ms	remaining: 862ms
812:	learn: 0.7174537	total: 950ms	remaining: 861ms
813:	learn: 0.7173237	total: 951ms	remaining: 860ms
814:	learn: 0.7171745	total: 952ms	remaining: 859ms
815:	learn: 0.7170238	total: 953ms	remaining: 858ms
816:	learn: 0.7168674	total: 955ms	remaining: 857ms
817:	learn: 0.7164875	total: 956ms	remaining: 855ms
818:	learn: 0.7162830	total: 957ms	remaining: 854ms
819:	learn: 0.7158600	total: 958ms	remaining: 853ms
820:	learn: 0.7155461	total: 960ms	remaining: 852ms
821:	learn: 0.7152777	total: 961ms	remaining: 851ms
822:	learn: 0.7149430	total: 962ms	remaining: 850ms
823:	learn: 0.7147390	total: 963ms	remaining: 849ms
824:	learn: 0.7145105	total: 964ms	remaining: 848ms
825:	learn: 0.7143146	total: 966ms	remaining: 846ms
826:	learn: 0.7141571	total: 967ms	remaining: 845ms
827:	learn: 0.7139529	total: 968ms	remaining: 844ms
828:	learn: 0.7138048	total: 969ms	remaining: 843ms
829:	learn: 0.7135551	total: 970ms	remaining: 842ms
830:	learn: 0.7131568	total: 972ms	remaining: 841ms
831:	learn: 0.7130071	total: 973ms	remaining: 839ms
832:	learn: 0.7125870	total: 974ms	remaining: 838ms
833:	learn: 0.7124684	total: 975ms	remaining: 837ms
834:	learn: 0.7122782	total: 976ms	remaining: 836ms
835:	learn: 0.7121178	total: 977ms	remaining: 835ms
836:	learn: 0.7119784	total: 979ms	remaining: 834ms
837:	learn: 0.7119188	total: 980ms	remaining: 833ms
838:	learn: 0.7116575	total: 981ms	remaining: 832ms
839:	learn: 0.7114706	total: 983ms	remaining: 831ms
840:	learn: 0.7111974	total: 984ms	remaining: 829ms
841:	learn: 0.7109580	total: 985ms	remaining: 828ms
842:	learn: 0.7108069	total: 986ms	remaining: 827ms
843:	learn: 0.7104821	total: 987ms	remaining: 826ms
844:	learn: 0.7103255	total: 988ms	remaining: 825ms
845:	learn: 0.7101769	total: 990ms	remaining: 824ms
846:	learn: 0.7098714	total: 991ms	remaining: 822ms
847:	learn: 0.7095557	total: 992ms	remaining: 821ms
848:	learn: 0.7092682	total: 993ms	remaining: 820ms
849:	learn: 0.7091003	total: 994ms	remaining: 819ms
850:	learn: 0.7088249	total: 996ms	remaining: 818ms
851:	learn: 0.7085542	total: 997ms	remaining: 817ms
852:	learn: 0.7083876	total: 998ms	remaining: 815ms
853:	learn: 0.7082403	total: 999ms	remaining: 814ms
854:	learn: 0.7080275	total: 1s	remaining: 813ms
855:	learn: 0.7078254	total: 1s	remaining: 812ms
856:	learn: 0.7077059	total: 1s	remaining: 811ms
857:	learn: 0.7075338	total: 1s	remaining: 810ms
858:	learn: 0.7071077	total: 1s	remaining: 808ms
859:	learn: 0.7069924	total: 1.01s	remaining: 807ms
860:	learn: 0.7068072	total: 1.01s	remaining: 806ms
861:	learn: 0.7065878	total: 1.01s	remaining: 805ms
862:	learn: 0.7061576	total: 1.01s	remaining: 804ms
863:	learn: 0.7060204	total: 1.01s	remaining: 802ms
864:	learn: 0.7059299	total: 1.01s	remaining: 801ms
865:	learn: 0.7056585	total: 1.01s	remaining: 800ms
866:	learn: 0.7053180	total: 1.01s	remaining: 799ms
867:	learn: 0.7052235	total: 1.01s	remaining: 798ms
868:	learn: 0.7051205	total: 1.02s	remaining: 797ms
869:	learn: 0.7047322	total: 1.02s	remaining: 796ms
870:	learn: 0.7045953	total: 1.02s	remaining: 794ms
871:	learn: 0.7042836	total: 1.02s	remaining: 793ms
872:	learn: 0.7041664	total: 1.02s	remaining: 792ms
873:	learn: 0.7040928	total: 1.02s	remaining: 791ms
874:	learn: 0.7038283	total: 1.02s	remaining: 790ms
875:	learn: 0.7036663	total: 1.02s	remaining: 789ms
876:	learn: 0.7035573	total: 1.03s	remaining: 788ms
877:	learn: 0.7032975	total: 1.03s	remaining: 786ms
878:	learn: 0.7032277	total: 1.03s	remaining: 785ms
879:	learn: 0.7028375	total: 1.03s	remaining: 784ms
880:	learn: 0.7027374	total: 1.03s	remaining: 783ms
881:	learn: 0.7024709	total: 1.03s	remaining: 781ms
882:	learn: 0.7023101	total: 1.03s	remaining: 780ms
883:	learn: 0.7018897	total: 1.03s	remaining: 779ms
884:	learn: 0.7018347	total: 1.03s	remaining: 778ms
885:	learn: 0.7015280	total: 1.04s	remaining: 777ms
886:	learn: 0.7013489	total: 1.04s	remaining: 776ms
887:	learn: 0.7012335	total: 1.04s	remaining: 775ms
888:	learn: 0.7010252	total: 1.04s	remaining: 773ms
889:	learn: 0.7009453	total: 1.04s	remaining: 772ms
890:	learn: 0.7008978	total: 1.04s	remaining: 771ms
891:	learn: 0.7007761	total: 1.04s	remaining: 770ms
892:	learn: 0.7006601	total: 1.04s	remaining: 769ms
893:	learn: 0.7001451	total: 1.05s	remaining: 768ms
894:	learn: 0.6998867	total: 1.05s	remaining: 767ms
895:	learn: 0.6997120	total: 1.05s	remaining: 766ms
896:	learn: 0.6995868	total: 1.05s	remaining: 765ms
897:	learn: 0.6993689	total: 1.05s	remaining: 763ms
898:	learn: 0.6992006	total: 1.05s	remaining: 762ms
899:	learn: 0.6991221	total: 1.05s	remaining: 761ms
900:	learn: 0.6989986	total: 1.05s	remaining: 760ms
901:	learn: 0.6987680	total: 1.06s	remaining: 759ms
902:	learn: 0.6981806	total: 1.06s	remaining: 758ms
903:	learn: 0.6979183	total: 1.06s	remaining: 757ms
904:	learn: 0.6977967	total: 1.06s	remaining: 756ms
905:	learn: 0.6976310	total: 1.06s	remaining: 755ms
906:	learn: 0.6975113	total: 1.06s	remaining: 754ms
907:	learn: 0.6973900	total: 1.06s	remaining: 752ms
908:	learn: 0.6972946	total: 1.06s	remaining: 751ms
909:	learn: 0.6971204	total: 1.07s	remaining: 750ms
910:	learn: 0.6969495	total: 1.07s	remaining: 749ms
911:	learn: 0.6968361	total: 1.07s	remaining: 748ms
912:	learn: 0.6966502	total: 1.07s	remaining: 747ms
913:	learn: 0.6965648	total: 1.07s	remaining: 746ms
914:	learn: 0.6960699	total: 1.07s	remaining: 745ms
915:	learn: 0.6956715	total: 1.07s	remaining: 744ms
916:	learn: 0.6955017	total: 1.07s	remaining: 742ms
917:	learn: 0.6953901	total: 1.08s	remaining: 741ms
918:	learn: 0.6953403	total: 1.08s	remaining: 740ms
919:	learn: 0.6950354	total: 1.08s	remaining: 739ms
920:	learn: 0.6948657	total: 1.08s	remaining: 738ms
921:	learn: 0.6946286	total: 1.08s	remaining: 737ms
922:	learn: 0.6944742	total: 1.08s	remaining: 736ms
923:	learn: 0.6943652	total: 1.08s	remaining: 735ms
924:	learn: 0.6938781	total: 1.08s	remaining: 734ms
925:	learn: 0.6935291	total: 1.09s	remaining: 733ms
926:	learn: 0.6934566	total: 1.09s	remaining: 731ms
927:	learn: 0.6933962	total: 1.09s	remaining: 730ms
928:	learn: 0.6932218	total: 1.09s	remaining: 729ms
929:	learn: 0.6930210	total: 1.09s	remaining: 728ms
930:	learn: 0.6927986	total: 1.09s	remaining: 727ms
931:	learn: 0.6926774	total: 1.09s	remaining: 726ms
932:	learn: 0.6924511	total: 1.09s	remaining: 725ms
933:	learn: 0.6924008	total: 1.1s	remaining: 724ms
934:	learn: 0.6919599	total: 1.1s	remaining: 722ms
935:	learn: 0.6916110	total: 1.1s	remaining: 722ms
936:	learn: 0.6913784	total: 1.1s	remaining: 721ms
937:	learn: 0.6911573	total: 1.1s	remaining: 720ms
938:	learn: 0.6908756	total: 1.1s	remaining: 719ms
939:	learn: 0.6907804	total: 1.1s	remaining: 718ms
940:	learn: 0.6904717	total: 1.11s	remaining: 717ms
941:	learn: 0.6901797	total: 1.11s	remaining: 715ms
942:	learn: 0.6900602	total: 1.11s	remaining: 714ms
943:	learn: 0.6899793	total: 1.11s	remaining: 713ms
944:	learn: 0.6897068	total: 1.11s	remaining: 712ms
945:	learn: 0.6894522	total: 1.11s	remaining: 711ms
946:	learn: 0.6891875	total: 1.11s	remaining: 710ms
947:	learn: 0.6889788	total: 1.12s	remaining: 709ms
948:	learn: 0.6887427	total: 1.12s	remaining: 708ms
949:	learn: 0.6886358	total: 1.12s	remaining: 707ms
950:	learn: 0.6883986	total: 1.12s	remaining: 706ms
951:	learn: 0.6880834	total: 1.12s	remaining: 705ms
952:	learn: 0.6879497	total: 1.12s	remaining: 704ms
953:	learn: 0.6878463	total: 1.12s	remaining: 703ms
954:	learn: 0.6874260	total: 1.13s	remaining: 702ms
955:	learn: 0.6869066	total: 1.13s	remaining: 701ms
956:	learn: 0.6865655	total: 1.13s	remaining: 699ms
957:	learn: 0.6864781	total: 1.13s	remaining: 698ms
958:	learn: 0.6860950	total: 1.13s	remaining: 697ms
959:	learn: 0.6860155	total: 1.13s	remaining: 696ms
960:	learn: 0.6859402	total: 1.13s	remaining: 695ms
961:	learn: 0.6855323	total: 1.14s	remaining: 694ms
962:	learn: 0.6853499	total: 1.14s	remaining: 693ms
963:	learn: 0.6847349	total: 1.14s	remaining: 692ms
964:	learn: 0.6844828	total: 1.14s	remaining: 691ms
965:	learn: 0.6843814	total: 1.14s	remaining: 690ms
966:	learn: 0.6841197	total: 1.14s	remaining: 688ms
967:	learn: 0.6840466	total: 1.14s	remaining: 687ms
968:	learn: 0.6838975	total: 1.14s	remaining: 686ms
969:	learn: 0.6838278	total: 1.15s	remaining: 685ms
970:	learn: 0.6833632	total: 1.15s	remaining: 684ms
971:	learn: 0.6832094	total: 1.15s	remaining: 683ms
972:	learn: 0.6828795	total: 1.15s	remaining: 682ms
973:	learn: 0.6823870	total: 1.15s	remaining: 681ms
974:	learn: 0.6818880	total: 1.15s	remaining: 680ms
975:	learn: 0.6817672	total: 1.15s	remaining: 678ms
976:	learn: 0.6816827	total: 1.15s	remaining: 677ms
977:	learn: 0.6814489	total: 1.16s	remaining: 676ms
978:	learn: 0.6811057	total: 1.16s	remaining: 675ms
979:	learn: 0.6809628	total: 1.16s	remaining: 674ms
980:	learn: 0.6806911	total: 1.16s	remaining: 673ms
981:	learn: 0.6804600	total: 1.16s	remaining: 672ms
982:	learn: 0.6802413	total: 1.16s	remaining: 670ms
983:	learn: 0.6797965	total: 1.16s	remaining: 669ms
984:	learn: 0.6792234	total: 1.16s	remaining: 668ms
985:	learn: 0.6791319	total: 1.17s	remaining: 667ms
986:	learn: 0.6790867	total: 1.17s	remaining: 666ms
987:	learn: 0.6789474	total: 1.17s	remaining: 665ms
988:	learn: 0.6786968	total: 1.17s	remaining: 664ms
989:	learn: 0.6783332	total: 1.17s	remaining: 662ms
990:	learn: 0.6781549	total: 1.17s	remaining: 661ms
991:	learn: 0.6780888	total: 1.17s	remaining: 660ms
992:	learn: 0.6778620	total: 1.18s	remaining: 659ms
993:	learn: 0.6776408	total: 1.18s	remaining: 658ms
994:	learn: 0.6774557	total: 1.18s	remaining: 657ms
995:	learn: 0.6773966	total: 1.18s	remaining: 656ms
996:	learn: 0.6770365	total: 1.18s	remaining: 655ms
997:	learn: 0.6769157	total: 1.18s	remaining: 654ms
998:	learn: 0.6768448	total: 1.18s	remaining: 652ms
999:	learn: 0.6765548	total: 1.18s	remaining: 651ms
1000:	learn: 0.6763596	total: 1.19s	remaining: 650ms
1001:	learn: 0.6762917	total: 1.19s	remaining: 649ms
1002:	learn: 0.6760432	total: 1.19s	remaining: 648ms
1003:	learn: 0.6756126	total: 1.19s	remaining: 647ms
1004:	learn: 0.6752433	total: 1.19s	remaining: 646ms
1005:	learn: 0.6747625	total: 1.19s	remaining: 645ms
1006:	learn: 0.6744970	total: 1.19s	remaining: 643ms
1007:	learn: 0.6743161	total: 1.19s	remaining: 642ms
1008:	learn: 0.6741890	total: 1.2s	remaining: 641ms
1009:	learn: 0.6740089	total: 1.2s	remaining: 640ms
1010:	learn: 0.6738233	total: 1.2s	remaining: 639ms
1011:	learn: 0.6735543	total: 1.2s	remaining: 638ms
1012:	learn: 0.6730449	total: 1.2s	remaining: 637ms
1013:	learn: 0.6728196	total: 1.2s	remaining: 636ms
1014:	learn: 0.6727668	total: 1.2s	remaining: 634ms
1015:	learn: 0.6723468	total: 1.2s	remaining: 633ms
1016:	learn: 0.6719259	total: 1.21s	remaining: 632ms
1017:	learn: 0.6717977	total: 1.21s	remaining: 631ms
1018:	learn: 0.6716372	total: 1.21s	remaining: 630ms
1019:	learn: 0.6714897	total: 1.21s	remaining: 629ms
1020:	learn: 0.6714398	total: 1.21s	remaining: 628ms
1021:	learn: 0.6710970	total: 1.21s	remaining: 626ms
1022:	learn: 0.6709715	total: 1.21s	remaining: 625ms
1023:	learn: 0.6707694	total: 1.22s	remaining: 624ms
1024:	learn: 0.6705043	total: 1.22s	remaining: 623ms
1025:	learn: 0.6703067	total: 1.22s	remaining: 622ms
1026:	learn: 0.6702199	total: 1.22s	remaining: 621ms
1027:	learn: 0.6700187	total: 1.22s	remaining: 620ms
1028:	learn: 0.6697463	total: 1.22s	remaining: 619ms
1029:	learn: 0.6694338	total: 1.22s	remaining: 617ms
1030:	learn: 0.6690795	total: 1.22s	remaining: 616ms
1031:	learn: 0.6689427	total: 1.23s	remaining: 615ms
1032:	learn: 0.6687809	total: 1.23s	remaining: 614ms
1033:	learn: 0.6687540	total: 1.23s	remaining: 613ms
1034:	learn: 0.6682127	total: 1.23s	remaining: 611ms
1035:	learn: 0.6681622	total: 1.23s	remaining: 610ms
1036:	learn: 0.6679063	total: 1.23s	remaining: 609ms
1037:	learn: 0.6676939	total: 1.23s	remaining: 608ms
1038:	learn: 0.6671296	total: 1.23s	remaining: 606ms
1039:	learn: 0.6665623	total: 1.23s	remaining: 605ms
1040:	learn: 0.6663355	total: 1.24s	remaining: 604ms
1041:	learn: 0.6663029	total: 1.24s	remaining: 603ms
1042:	learn: 0.6658967	total: 1.24s	remaining: 601ms
1043:	learn: 0.6657559	total: 1.24s	remaining: 600ms
1044:	learn: 0.6655931	total: 1.24s	remaining: 599ms
1045:	learn: 0.6650709	total: 1.24s	remaining: 598ms
1046:	learn: 0.6649476	total: 1.24s	remaining: 597ms
1047:	learn: 0.6647856	total: 1.24s	remaining: 596ms
1048:	learn: 0.6643773	total: 1.24s	remaining: 594ms
1049:	learn: 0.6639392	total: 1.25s	remaining: 593ms
1050:	learn: 0.6633885	total: 1.25s	remaining: 592ms
1051:	learn: 0.6629526	total: 1.25s	remaining: 591ms
1052:	learn: 0.6625284	total: 1.25s	remaining: 590ms
1053:	learn: 0.6624700	total: 1.25s	remaining: 589ms
1054:	learn: 0.6621771	total: 1.25s	remaining: 587ms
1055:	learn: 0.6617624	total: 1.25s	remaining: 586ms
1056:	learn: 0.6615691	total: 1.25s	remaining: 585ms
1057:	learn: 0.6612363	total: 1.25s	remaining: 584ms
1058:	learn: 0.6611382	total: 1.26s	remaining: 583ms
1059:	learn: 0.6609054	total: 1.26s	remaining: 582ms
1060:	learn: 0.6606896	total: 1.26s	remaining: 581ms
1061:	learn: 0.6605635	total: 1.26s	remaining: 579ms
1062:	learn: 0.6603496	total: 1.26s	remaining: 578ms
1063:	learn: 0.6601465	total: 1.26s	remaining: 577ms
1064:	learn: 0.6597287	total: 1.26s	remaining: 576ms
1065:	learn: 0.6595448	total: 1.27s	remaining: 575ms
1066:	learn: 0.6590359	total: 1.27s	remaining: 574ms
1067:	learn: 0.6585991	total: 1.27s	remaining: 573ms
1068:	learn: 0.6582229	total: 1.27s	remaining: 571ms
1069:	learn: 0.6580500	total: 1.27s	remaining: 570ms
1070:	learn: 0.6579617	total: 1.27s	remaining: 569ms
1071:	learn: 0.6575744	total: 1.27s	remaining: 568ms
1072:	learn: 0.6574318	total: 1.27s	remaining: 567ms
1073:	learn: 0.6571820	total: 1.28s	remaining: 566ms
1074:	learn: 0.6566891	total: 1.28s	remaining: 565ms
1075:	learn: 0.6564309	total: 1.28s	remaining: 564ms
1076:	learn: 0.6560103	total: 1.28s	remaining: 563ms
1077:	learn: 0.6559791	total: 1.28s	remaining: 561ms
1078:	learn: 0.6559183	total: 1.28s	remaining: 560ms
1079:	learn: 0.6558018	total: 1.28s	remaining: 559ms
1080:	learn: 0.6553731	total: 1.28s	remaining: 558ms
1081:	learn: 0.6550188	total: 1.29s	remaining: 557ms
1082:	learn: 0.6548480	total: 1.29s	remaining: 555ms
1083:	learn: 0.6544240	total: 1.29s	remaining: 554ms
1084:	learn: 0.6542635	total: 1.29s	remaining: 553ms
1085:	learn: 0.6541271	total: 1.29s	remaining: 552ms
1086:	learn: 0.6539950	total: 1.29s	remaining: 551ms
1087:	learn: 0.6537354	total: 1.29s	remaining: 550ms
1088:	learn: 0.6535979	total: 1.3s	remaining: 549ms
1089:	learn: 0.6531778	total: 1.3s	remaining: 548ms
1090:	learn: 0.6527124	total: 1.3s	remaining: 547ms
1091:	learn: 0.6525839	total: 1.3s	remaining: 545ms
1092:	learn: 0.6523310	total: 1.3s	remaining: 544ms
1093:	learn: 0.6518172	total: 1.3s	remaining: 543ms
1094:	learn: 0.6517548	total: 1.3s	remaining: 542ms
1095:	learn: 0.6514167	total: 1.31s	remaining: 541ms
1096:	learn: 0.6509442	total: 1.31s	remaining: 540ms
1097:	learn: 0.6509064	total: 1.31s	remaining: 539ms
1098:	learn: 0.6508171	total: 1.31s	remaining: 538ms
1099:	learn: 0.6506057	total: 1.31s	remaining: 537ms
1100:	learn: 0.6501442	total: 1.31s	remaining: 535ms
1101:	learn: 0.6497151	total: 1.31s	remaining: 534ms
1102:	learn: 0.6494010	total: 1.31s	remaining: 533ms
1103:	learn: 0.6493369	total: 1.32s	remaining: 532ms
1104:	learn: 0.6490621	total: 1.32s	remaining: 531ms
1105:	learn: 0.6488271	total: 1.32s	remaining: 530ms
1106:	learn: 0.6485559	total: 1.32s	remaining: 529ms
1107:	learn: 0.6481559	total: 1.32s	remaining: 527ms
1108:	learn: 0.6477647	total: 1.32s	remaining: 526ms
1109:	learn: 0.6474373	total: 1.32s	remaining: 525ms
1110:	learn: 0.6472578	total: 1.33s	remaining: 524ms
1111:	learn: 0.6468158	total: 1.33s	remaining: 523ms
1112:	learn: 0.6466910	total: 1.33s	remaining: 522ms
1113:	learn: 0.6465645	total: 1.33s	remaining: 521ms
1114:	learn: 0.6462460	total: 1.33s	remaining: 519ms
1115:	learn: 0.6458098	total: 1.33s	remaining: 518ms
1116:	learn: 0.6453429	total: 1.33s	remaining: 517ms
1117:	learn: 0.6449829	total: 1.33s	remaining: 516ms
1118:	learn: 0.6448019	total: 1.34s	remaining: 515ms
1119:	learn: 0.6444540	total: 1.34s	remaining: 514ms
1120:	learn: 0.6440600	total: 1.34s	remaining: 513ms
1121:	learn: 0.6437180	total: 1.34s	remaining: 512ms
1122:	learn: 0.6432811	total: 1.34s	remaining: 510ms
1123:	learn: 0.6428433	total: 1.34s	remaining: 509ms
1124:	learn: 0.6427307	total: 1.34s	remaining: 508ms
1125:	learn: 0.6422715	total: 1.35s	remaining: 507ms
1126:	learn: 0.6419569	total: 1.35s	remaining: 506ms
1127:	learn: 0.6415606	total: 1.35s	remaining: 505ms
1128:	learn: 0.6413310	total: 1.35s	remaining: 504ms
1129:	learn: 0.6412404	total: 1.35s	remaining: 502ms
1130:	learn: 0.6407402	total: 1.35s	remaining: 501ms
1131:	learn: 0.6406180	total: 1.35s	remaining: 500ms
1132:	learn: 0.6401969	total: 1.35s	remaining: 499ms
1133:	learn: 0.6400009	total: 1.36s	remaining: 498ms
1134:	learn: 0.6396075	total: 1.36s	remaining: 497ms
1135:	learn: 0.6394379	total: 1.36s	remaining: 496ms
1136:	learn: 0.6393378	total: 1.36s	remaining: 494ms
1137:	learn: 0.6391457	total: 1.36s	remaining: 493ms
1138:	learn: 0.6387027	total: 1.36s	remaining: 492ms
1139:	learn: 0.6386590	total: 1.36s	remaining: 491ms
1140:	learn: 0.6383429	total: 1.37s	remaining: 490ms
1141:	learn: 0.6382277	total: 1.37s	remaining: 489ms
1142:	learn: 0.6379865	total: 1.37s	remaining: 487ms
1143:	learn: 0.6375688	total: 1.37s	remaining: 486ms
1144:	learn: 0.6375251	total: 1.37s	remaining: 485ms
1145:	learn: 0.6373705	total: 1.37s	remaining: 484ms
1146:	learn: 0.6372544	total: 1.37s	remaining: 483ms
1147:	learn: 0.6371271	total: 1.38s	remaining: 482ms
1148:	learn: 0.6370949	total: 1.38s	remaining: 481ms
1149:	learn: 0.6369145	total: 1.38s	remaining: 480ms
1150:	learn: 0.6367210	total: 1.38s	remaining: 478ms
1151:	learn: 0.6366061	total: 1.38s	remaining: 477ms
1152:	learn: 0.6364979	total: 1.38s	remaining: 476ms
1153:	learn: 0.6362777	total: 1.38s	remaining: 475ms
1154:	learn: 0.6360981	total: 1.39s	remaining: 474ms
1155:	learn: 0.6359737	total: 1.39s	remaining: 473ms
1156:	learn: 0.6358136	total: 1.39s	remaining: 472ms
1157:	learn: 0.6353795	total: 1.39s	remaining: 470ms
1158:	learn: 0.6351992	total: 1.39s	remaining: 469ms
1159:	learn: 0.6350303	total: 1.39s	remaining: 468ms
1160:	learn: 0.6348382	total: 1.39s	remaining: 467ms
1161:	learn: 0.6348091	total: 1.39s	remaining: 466ms
1162:	learn: 0.6345903	total: 1.4s	remaining: 465ms
1163:	learn: 0.6345112	total: 1.4s	remaining: 463ms
1164:	learn: 0.6344021	total: 1.4s	remaining: 462ms
1165:	learn: 0.6342865	total: 1.4s	remaining: 461ms
1166:	learn: 0.6342574	total: 1.4s	remaining: 460ms
1167:	learn: 0.6338125	total: 1.4s	remaining: 459ms
1168:	learn: 0.6335329	total: 1.4s	remaining: 457ms
1169:	learn: 0.6334982	total: 1.4s	remaining: 456ms
1170:	learn: 0.6332884	total: 1.41s	remaining: 455ms
1171:	learn: 0.6332605	total: 1.41s	remaining: 454ms
1172:	learn: 0.6330267	total: 1.41s	remaining: 453ms
1173:	learn: 0.6329015	total: 1.41s	remaining: 452ms
1174:	learn: 0.6325161	total: 1.41s	remaining: 450ms
1175:	learn: 0.6322426	total: 1.41s	remaining: 449ms
1176:	learn: 0.6321011	total: 1.41s	remaining: 448ms
1177:	learn: 0.6317828	total: 1.42s	remaining: 447ms
1178:	learn: 0.6315856	total: 1.42s	remaining: 446ms
1179:	learn: 0.6312283	total: 1.42s	remaining: 445ms
1180:	learn: 0.6311269	total: 1.42s	remaining: 443ms
1181:	learn: 0.6306963	total: 1.42s	remaining: 442ms
1182:	learn: 0.6305877	total: 1.42s	remaining: 441ms
1183:	learn: 0.6301736	total: 1.42s	remaining: 440ms
1184:	learn: 0.6300662	total: 1.42s	remaining: 439ms
1185:	learn: 0.6299181	total: 1.43s	remaining: 438ms
1186:	learn: 0.6294894	total: 1.43s	remaining: 436ms
1187:	learn: 0.6290676	total: 1.43s	remaining: 435ms
1188:	learn: 0.6289345	total: 1.43s	remaining: 434ms
1189:	learn: 0.6288802	total: 1.43s	remaining: 433ms
1190:	learn: 0.6284832	total: 1.43s	remaining: 432ms
1191:	learn: 0.6283689	total: 1.43s	remaining: 430ms
1192:	learn: 0.6282634	total: 1.43s	remaining: 429ms
1193:	learn: 0.6280944	total: 1.44s	remaining: 428ms
1194:	learn: 0.6276200	total: 1.44s	remaining: 427ms
1195:	learn: 0.6272205	total: 1.44s	remaining: 426ms
1196:	learn: 0.6268634	total: 1.44s	remaining: 424ms
1197:	learn: 0.6267793	total: 1.44s	remaining: 423ms
1198:	learn: 0.6263614	total: 1.44s	remaining: 422ms
1199:	learn: 0.6261001	total: 1.44s	remaining: 421ms
1200:	learn: 0.6257024	total: 1.44s	remaining: 420ms
1201:	learn: 0.6255809	total: 1.45s	remaining: 418ms
1202:	learn: 0.6252844	total: 1.45s	remaining: 417ms
1203:	learn: 0.6251865	total: 1.45s	remaining: 416ms
1204:	learn: 0.6249836	total: 1.45s	remaining: 415ms
1205:	learn: 0.6247837	total: 1.45s	remaining: 414ms
1206:	learn: 0.6244208	total: 1.45s	remaining: 412ms
1207:	learn: 0.6241507	total: 1.45s	remaining: 411ms
1208:	learn: 0.6241177	total: 1.45s	remaining: 410ms
1209:	learn: 0.6240844	total: 1.45s	remaining: 409ms
1210:	learn: 0.6237291	total: 1.46s	remaining: 408ms
1211:	learn: 0.6236066	total: 1.46s	remaining: 406ms
1212:	learn: 0.6232705	total: 1.46s	remaining: 405ms
1213:	learn: 0.6228667	total: 1.46s	remaining: 404ms
1214:	learn: 0.6225105	total: 1.46s	remaining: 403ms
1215:	learn: 0.6222190	total: 1.46s	remaining: 401ms
1216:	learn: 0.6218413	total: 1.46s	remaining: 400ms
1217:	learn: 0.6214452	total: 1.46s	remaining: 399ms
1218:	learn: 0.6213954	total: 1.47s	remaining: 398ms
1219:	learn: 0.6209847	total: 1.47s	remaining: 397ms
1220:	learn: 0.6206077	total: 1.47s	remaining: 395ms
1221:	learn: 0.6205094	total: 1.47s	remaining: 394ms
1222:	learn: 0.6203119	total: 1.47s	remaining: 393ms
1223:	learn: 0.6201962	total: 1.47s	remaining: 392ms
1224:	learn: 0.6199085	total: 1.47s	remaining: 390ms
1225:	learn: 0.6198765	total: 1.47s	remaining: 389ms
1226:	learn: 0.6197086	total: 1.47s	remaining: 388ms
1227:	learn: 0.6193925	total: 1.48s	remaining: 387ms
1228:	learn: 0.6188942	total: 1.48s	remaining: 386ms
1229:	learn: 0.6184971	total: 1.48s	remaining: 384ms
1230:	learn: 0.6182758	total: 1.48s	remaining: 383ms
1231:	learn: 0.6179239	total: 1.48s	remaining: 382ms
1232:	learn: 0.6175462	total: 1.48s	remaining: 381ms
1233:	learn: 0.6174088	total: 1.48s	remaining: 380ms
1234:	learn: 0.6170054	total: 1.48s	remaining: 378ms
1235:	learn: 0.6168516	total: 1.48s	remaining: 377ms
1236:	learn: 0.6164527	total: 1.49s	remaining: 376ms
1237:	learn: 0.6163538	total: 1.49s	remaining: 375ms
1238:	learn: 0.6160065	total: 1.49s	remaining: 373ms
1239:	learn: 0.6158248	total: 1.49s	remaining: 372ms
1240:	learn: 0.6155307	total: 1.49s	remaining: 371ms
1241:	learn: 0.6151297	total: 1.49s	remaining: 370ms
1242:	learn: 0.6148835	total: 1.49s	remaining: 369ms
1243:	learn: 0.6146963	total: 1.49s	remaining: 367ms
1244:	learn: 0.6146017	total: 1.49s	remaining: 366ms
1245:	learn: 0.6144906	total: 1.5s	remaining: 365ms
1246:	learn: 0.6141540	total: 1.5s	remaining: 364ms
1247:	learn: 0.6138388	total: 1.5s	remaining: 363ms
1248:	learn: 0.6136429	total: 1.5s	remaining: 361ms
1249:	learn: 0.6132937	total: 1.5s	remaining: 360ms
1250:	learn: 0.6131860	total: 1.5s	remaining: 359ms
1251:	learn: 0.6129080	total: 1.5s	remaining: 358ms
1252:	learn: 0.6126708	total: 1.5s	remaining: 356ms
1253:	learn: 0.6124020	total: 1.5s	remaining: 355ms
1254:	learn: 0.6122751	total: 1.51s	remaining: 354ms
1255:	learn: 0.6122292	total: 1.51s	remaining: 353ms
1256:	learn: 0.6119410	total: 1.51s	remaining: 352ms
1257:	learn: 0.6116472	total: 1.51s	remaining: 350ms
1258:	learn: 0.6113350	total: 1.51s	remaining: 349ms
1259:	learn: 0.6112290	total: 1.51s	remaining: 348ms
1260:	learn: 0.6110082	total: 1.51s	remaining: 347ms
1261:	learn: 0.6106579	total: 1.51s	remaining: 346ms
1262:	learn: 0.6103905	total: 1.51s	remaining: 344ms
1263:	learn: 0.6102491	total: 1.52s	remaining: 343ms
1264:	learn: 0.6101927	total: 1.52s	remaining: 342ms
1265:	learn: 0.6100674	total: 1.52s	remaining: 341ms
1266:	learn: 0.6096575	total: 1.52s	remaining: 339ms
1267:	learn: 0.6093449	total: 1.52s	remaining: 338ms
1268:	learn: 0.6089290	total: 1.52s	remaining: 337ms
1269:	learn: 0.6087517	total: 1.52s	remaining: 336ms
1270:	learn: 0.6085157	total: 1.52s	remaining: 335ms
1271:	learn: 0.6080895	total: 1.52s	remaining: 334ms
1272:	learn: 0.6078602	total: 1.53s	remaining: 332ms
1273:	learn: 0.6077052	total: 1.53s	remaining: 331ms
1274:	learn: 0.6073688	total: 1.53s	remaining: 330ms
1275:	learn: 0.6070406	total: 1.53s	remaining: 329ms
1276:	learn: 0.6067139	total: 1.53s	remaining: 327ms
1277:	learn: 0.6065826	total: 1.53s	remaining: 326ms
1278:	learn: 0.6063468	total: 1.53s	remaining: 325ms
1279:	learn: 0.6062849	total: 1.53s	remaining: 324ms
1280:	learn: 0.6061447	total: 1.54s	remaining: 323ms
1281:	learn: 0.6059765	total: 1.54s	remaining: 321ms
1282:	learn: 0.6057890	total: 1.54s	remaining: 320ms
1283:	learn: 0.6055013	total: 1.54s	remaining: 319ms
1284:	learn: 0.6053796	total: 1.54s	remaining: 318ms
1285:	learn: 0.6052847	total: 1.54s	remaining: 317ms
1286:	learn: 0.6050563	total: 1.54s	remaining: 315ms
1287:	learn: 0.6049150	total: 1.54s	remaining: 314ms
1288:	learn: 0.6045214	total: 1.54s	remaining: 313ms
1289:	learn: 0.6042134	total: 1.55s	remaining: 312ms
1290:	learn: 0.6040304	total: 1.55s	remaining: 311ms
1291:	learn: 0.6036764	total: 1.55s	remaining: 309ms
1292:	learn: 0.6033631	total: 1.55s	remaining: 308ms
1293:	learn: 0.6031153	total: 1.55s	remaining: 307ms
1294:	learn: 0.6029354	total: 1.55s	remaining: 306ms
1295:	learn: 0.6026342	total: 1.55s	remaining: 305ms
1296:	learn: 0.6021567	total: 1.55s	remaining: 303ms
1297:	learn: 0.6017696	total: 1.56s	remaining: 302ms
1298:	learn: 0.6014257	total: 1.56s	remaining: 301ms
1299:	learn: 0.6011285	total: 1.56s	remaining: 300ms
1300:	learn: 0.6010159	total: 1.56s	remaining: 299ms
1301:	learn: 0.6007098	total: 1.56s	remaining: 297ms
1302:	learn: 0.6004918	total: 1.56s	remaining: 296ms
1303:	learn: 0.6001682	total: 1.56s	remaining: 295ms
1304:	learn: 0.5998679	total: 1.56s	remaining: 294ms
1305:	learn: 0.5995953	total: 1.57s	remaining: 293ms
1306:	learn: 0.5993871	total: 1.57s	remaining: 291ms
1307:	learn: 0.5991745	total: 1.57s	remaining: 290ms
1308:	learn: 0.5987829	total: 1.57s	remaining: 289ms
1309:	learn: 0.5987539	total: 1.57s	remaining: 288ms
1310:	learn: 0.5985629	total: 1.57s	remaining: 287ms
1311:	learn: 0.5980587	total: 1.57s	remaining: 285ms
1312:	learn: 0.5980087	total: 1.57s	remaining: 284ms
1313:	learn: 0.5976708	total: 1.58s	remaining: 283ms
1314:	learn: 0.5975756	total: 1.58s	remaining: 282ms
1315:	learn: 0.5973893	total: 1.58s	remaining: 281ms
1316:	learn: 0.5972618	total: 1.58s	remaining: 280ms
1317:	learn: 0.5968246	total: 1.58s	remaining: 278ms
1318:	learn: 0.5967466	total: 1.58s	remaining: 277ms
1319:	learn: 0.5964730	total: 1.58s	remaining: 276ms
1320:	learn: 0.5963255	total: 1.58s	remaining: 275ms
1321:	learn: 0.5962377	total: 1.59s	remaining: 274ms
1322:	learn: 0.5960157	total: 1.59s	remaining: 272ms
1323:	learn: 0.5957153	total: 1.59s	remaining: 271ms
1324:	learn: 0.5955749	total: 1.59s	remaining: 270ms
1325:	learn: 0.5952299	total: 1.59s	remaining: 269ms
1326:	learn: 0.5948778	total: 1.59s	remaining: 268ms
1327:	learn: 0.5946805	total: 1.59s	remaining: 267ms
1328:	learn: 0.5943947	total: 1.6s	remaining: 265ms
1329:	learn: 0.5943060	total: 1.6s	remaining: 264ms
1330:	learn: 0.5940172	total: 1.6s	remaining: 263ms
1331:	learn: 0.5938961	total: 1.6s	remaining: 262ms
1332:	learn: 0.5938411	total: 1.6s	remaining: 261ms
1333:	learn: 0.5937204	total: 1.6s	remaining: 259ms
1334:	learn: 0.5935352	total: 1.6s	remaining: 258ms
1335:	learn: 0.5934623	total: 1.6s	remaining: 257ms
1336:	learn: 0.5933172	total: 1.6s	remaining: 256ms
1337:	learn: 0.5929878	total: 1.61s	remaining: 255ms
1338:	learn: 0.5926567	total: 1.61s	remaining: 253ms
1339:	learn: 0.5923999	total: 1.61s	remaining: 252ms
1340:	learn: 0.5921104	total: 1.61s	remaining: 251ms
1341:	learn: 0.5918808	total: 1.61s	remaining: 250ms
1342:	learn: 0.5916305	total: 1.61s	remaining: 249ms
1343:	learn: 0.5912685	total: 1.61s	remaining: 247ms
1344:	learn: 0.5911868	total: 1.61s	remaining: 246ms
1345:	learn: 0.5909052	total: 1.62s	remaining: 245ms
1346:	learn: 0.5908653	total: 1.62s	remaining: 244ms
1347:	learn: 0.5906021	total: 1.62s	remaining: 243ms
1348:	learn: 0.5904478	total: 1.62s	remaining: 241ms
1349:	learn: 0.5901461	total: 1.62s	remaining: 240ms
1350:	learn: 0.5897039	total: 1.62s	remaining: 239ms
1351:	learn: 0.5896007	total: 1.62s	remaining: 238ms
1352:	learn: 0.5893483	total: 1.62s	remaining: 237ms
1353:	learn: 0.5891705	total: 1.63s	remaining: 235ms
1354:	learn: 0.5889526	total: 1.63s	remaining: 234ms
1355:	learn: 0.5887715	total: 1.63s	remaining: 233ms
1356:	learn: 0.5886204	total: 1.63s	remaining: 232ms
1357:	learn: 0.5883486	total: 1.63s	remaining: 231ms
1358:	learn: 0.5882742	total: 1.63s	remaining: 229ms
1359:	learn: 0.5877882	total: 1.63s	remaining: 228ms
1360:	learn: 0.5875750	total: 1.63s	remaining: 227ms
1361:	learn: 0.5872317	total: 1.64s	remaining: 226ms
1362:	learn: 0.5869559	total: 1.64s	remaining: 225ms
1363:	learn: 0.5869105	total: 1.64s	remaining: 223ms
1364:	learn: 0.5865650	total: 1.64s	remaining: 222ms
1365:	learn: 0.5862435	total: 1.64s	remaining: 221ms
1366:	learn: 0.5858943	total: 1.64s	remaining: 220ms
1367:	learn: 0.5854611	total: 1.64s	remaining: 219ms
1368:	learn: 0.5852265	total: 1.64s	remaining: 217ms
1369:	learn: 0.5851038	total: 1.65s	remaining: 216ms
1370:	learn: 0.5847235	total: 1.65s	remaining: 215ms
1371:	learn: 0.5843467	total: 1.65s	remaining: 214ms
1372:	learn: 0.5839985	total: 1.65s	remaining: 213ms
1373:	learn: 0.5838614	total: 1.65s	remaining: 211ms
1374:	learn: 0.5834425	total: 1.65s	remaining: 210ms
1375:	learn: 0.5831247	total: 1.65s	remaining: 209ms
1376:	learn: 0.5828293	total: 1.65s	remaining: 208ms
1377:	learn: 0.5828012	total: 1.66s	remaining: 207ms
1378:	learn: 0.5824821	total: 1.66s	remaining: 205ms
1379:	learn: 0.5823302	total: 1.66s	remaining: 204ms
1380:	learn: 0.5822952	total: 1.66s	remaining: 203ms
1381:	learn: 0.5819644	total: 1.66s	remaining: 202ms
1382:	learn: 0.5818232	total: 1.66s	remaining: 201ms
1383:	learn: 0.5816872	total: 1.66s	remaining: 199ms
1384:	learn: 0.5813028	total: 1.66s	remaining: 198ms
1385:	learn: 0.5810889	total: 1.67s	remaining: 197ms
1386:	learn: 0.5807848	total: 1.67s	remaining: 196ms
1387:	learn: 0.5806508	total: 1.67s	remaining: 195ms
1388:	learn: 0.5803323	total: 1.67s	remaining: 193ms
1389:	learn: 0.5800367	total: 1.67s	remaining: 192ms
1390:	learn: 0.5796523	total: 1.67s	remaining: 191ms
1391:	learn: 0.5795905	total: 1.67s	remaining: 190ms
1392:	learn: 0.5793718	total: 1.67s	remaining: 189ms
1393:	learn: 0.5789732	total: 1.68s	remaining: 188ms
1394:	learn: 0.5788335	total: 1.68s	remaining: 186ms
1395:	learn: 0.5785427	total: 1.68s	remaining: 185ms
1396:	learn: 0.5782713	total: 1.68s	remaining: 184ms
1397:	learn: 0.5780244	total: 1.68s	remaining: 183ms
1398:	learn: 0.5779524	total: 1.68s	remaining: 182ms
1399:	learn: 0.5776390	total: 1.68s	remaining: 180ms
1400:	learn: 0.5773431	total: 1.68s	remaining: 179ms
1401:	learn: 0.5769470	total: 1.69s	remaining: 178ms
1402:	learn: 0.5767052	total: 1.69s	remaining: 177ms
1403:	learn: 0.5764846	total: 1.69s	remaining: 176ms
1404:	learn: 0.5760700	total: 1.69s	remaining: 174ms
1405:	learn: 0.5756776	total: 1.69s	remaining: 173ms
1406:	learn: 0.5754415	total: 1.69s	remaining: 172ms
1407:	learn: 0.5749613	total: 1.69s	remaining: 171ms
1408:	learn: 0.5747842	total: 1.7s	remaining: 170ms
1409:	learn: 0.5744872	total: 1.7s	remaining: 168ms
1410:	learn: 0.5743156	total: 1.7s	remaining: 167ms
1411:	learn: 0.5739598	total: 1.7s	remaining: 166ms
1412:	learn: 0.5736081	total: 1.7s	remaining: 165ms
1413:	learn: 0.5732247	total: 1.7s	remaining: 164ms
1414:	learn: 0.5731124	total: 1.7s	remaining: 162ms
1415:	learn: 0.5728142	total: 1.7s	remaining: 161ms
1416:	learn: 0.5724832	total: 1.71s	remaining: 160ms
1417:	learn: 0.5721831	total: 1.71s	remaining: 159ms
1418:	learn: 0.5718999	total: 1.71s	remaining: 158ms
1419:	learn: 0.5715576	total: 1.71s	remaining: 157ms
1420:	learn: 0.5711413	total: 1.71s	remaining: 155ms
1421:	learn: 0.5709636	total: 1.71s	remaining: 154ms
1422:	learn: 0.5706839	total: 1.71s	remaining: 153ms
1423:	learn: 0.5703855	total: 1.71s	remaining: 152ms
1424:	learn: 0.5701159	total: 1.72s	remaining: 151ms
1425:	learn: 0.5697868	total: 1.72s	remaining: 149ms
1426:	learn: 0.5693993	total: 1.72s	remaining: 148ms
1427:	learn: 0.5691188	total: 1.72s	remaining: 147ms
1428:	learn: 0.5689682	total: 1.72s	remaining: 146ms
1429:	learn: 0.5687503	total: 1.72s	remaining: 145ms
1430:	learn: 0.5687099	total: 1.72s	remaining: 143ms
1431:	learn: 0.5685235	total: 1.73s	remaining: 142ms
1432:	learn: 0.5682079	total: 1.73s	remaining: 141ms
1433:	learn: 0.5680082	total: 1.73s	remaining: 140ms
1434:	learn: 0.5677525	total: 1.73s	remaining: 139ms
1435:	learn: 0.5673539	total: 1.73s	remaining: 137ms
1436:	learn: 0.5669106	total: 1.73s	remaining: 136ms
1437:	learn: 0.5665817	total: 1.73s	remaining: 135ms
1438:	learn: 0.5661980	total: 1.73s	remaining: 134ms
1439:	learn: 0.5660982	total: 1.74s	remaining: 133ms
1440:	learn: 0.5657968	total: 1.74s	remaining: 131ms
1441:	learn: 0.5655863	total: 1.74s	remaining: 130ms
1442:	learn: 0.5653378	total: 1.74s	remaining: 129ms
1443:	learn: 0.5650026	total: 1.74s	remaining: 128ms
1444:	learn: 0.5648361	total: 1.74s	remaining: 127ms
1445:	learn: 0.5644608	total: 1.74s	remaining: 125ms
1446:	learn: 0.5642395	total: 1.74s	remaining: 124ms
1447:	learn: 0.5640222	total: 1.74s	remaining: 123ms
1448:	learn: 0.5639938	total: 1.75s	remaining: 122ms
1449:	learn: 0.5637161	total: 1.75s	remaining: 121ms
1450:	learn: 0.5635542	total: 1.75s	remaining: 119ms
1451:	learn: 0.5633772	total: 1.75s	remaining: 118ms
1452:	learn: 0.5633050	total: 1.75s	remaining: 117ms
1453:	learn: 0.5629255	total: 1.75s	remaining: 116ms
1454:	learn: 0.5626279	total: 1.75s	remaining: 115ms
1455:	learn: 0.5622156	total: 1.75s	remaining: 113ms
1456:	learn: 0.5619867	total: 1.76s	remaining: 112ms
1457:	learn: 0.5615833	total: 1.76s	remaining: 111ms
1458:	learn: 0.5612347	total: 1.76s	remaining: 110ms
1459:	learn: 0.5608648	total: 1.76s	remaining: 109ms
1460:	learn: 0.5605262	total: 1.76s	remaining: 107ms
1461:	learn: 0.5602744	total: 1.76s	remaining: 106ms
1462:	learn: 0.5601511	total: 1.76s	remaining: 105ms
1463:	learn: 0.5600734	total: 1.76s	remaining: 104ms
1464:	learn: 0.5600184	total: 1.77s	remaining: 102ms
1465:	learn: 0.5599192	total: 1.77s	remaining: 101ms
1466:	learn: 0.5594882	total: 1.77s	remaining: 100ms
1467:	learn: 0.5593865	total: 1.77s	remaining: 98.8ms
1468:	learn: 0.5591642	total: 1.77s	remaining: 97.6ms
1469:	learn: 0.5588173	total: 1.77s	remaining: 96.4ms
1470:	learn: 0.5585407	total: 1.77s	remaining: 95.2ms
1471:	learn: 0.5582549	total: 1.77s	remaining: 94ms
1472:	learn: 0.5578805	total: 1.77s	remaining: 92.8ms
1473:	learn: 0.5577095	total: 1.78s	remaining: 91.6ms
1474:	learn: 0.5575814	total: 1.78s	remaining: 90.4ms
1475:	learn: 0.5573884	total: 1.78s	remaining: 89.2ms
1476:	learn: 0.5571651	total: 1.78s	remaining: 88ms
1477:	learn: 0.5569445	total: 1.78s	remaining: 86.8ms
1478:	learn: 0.5567152	total: 1.78s	remaining: 85.6ms
1479:	learn: 0.5564232	total: 1.78s	remaining: 84.4ms
1480:	learn: 0.5562158	total: 1.78s	remaining: 83.2ms
1481:	learn: 0.5559245	total: 1.79s	remaining: 82ms
1482:	learn: 0.5557135	total: 1.79s	remaining: 80.7ms
1483:	learn: 0.5555792	total: 1.79s	remaining: 79.5ms
1484:	learn: 0.5554351	total: 1.79s	remaining: 78.3ms
1485:	learn: 0.5551167	total: 1.79s	remaining: 77.1ms
1486:	learn: 0.5549052	total: 1.79s	remaining: 75.9ms
1487:	learn: 0.5546166	total: 1.79s	remaining: 74.7ms
1488:	learn: 0.5545081	total: 1.79s	remaining: 73.5ms
1489:	learn: 0.5544655	total: 1.79s	remaining: 72.3ms
1490:	learn: 0.5542661	total: 1.8s	remaining: 71.1ms
1491:	learn: 0.5540913	total: 1.8s	remaining: 69.9ms
1492:	learn: 0.5540530	total: 1.8s	remaining: 68.7ms
1493:	learn: 0.5537815	total: 1.8s	remaining: 67.5ms
1494:	learn: 0.5535082	total: 1.8s	remaining: 66.3ms
1495:	learn: 0.5532076	total: 1.8s	remaining: 65.1ms
1496:	learn: 0.5528970	total: 1.8s	remaining: 63.9ms
1497:	learn: 0.5524127	total: 1.8s	remaining: 62.7ms
1498:	learn: 0.5521608	total: 1.81s	remaining: 61.5ms
1499:	learn: 0.5519224	total: 1.81s	remaining: 60.2ms
1500:	learn: 0.5516799	total: 1.81s	remaining: 59ms
1501:	learn: 0.5513902	total: 1.81s	remaining: 57.8ms
1502:	learn: 0.5512200	total: 1.81s	remaining: 56.6ms
1503:	learn: 0.5508671	total: 1.81s	remaining: 55.4ms
1504:	learn: 0.5507077	total: 1.81s	remaining: 54.2ms
1505:	learn: 0.5504047	total: 1.81s	remaining: 53ms
1506:	learn: 0.5502013	total: 1.81s	remaining: 51.8ms
1507:	learn: 0.5499843	total: 1.82s	remaining: 50.6ms
1508:	learn: 0.5496157	total: 1.82s	remaining: 49.4ms
1509:	learn: 0.5494189	total: 1.82s	remaining: 48.2ms
1510:	learn: 0.5493356	total: 1.82s	remaining: 47ms
1511:	learn: 0.5492746	total: 1.82s	remaining: 45.8ms
1512:	learn: 0.5492003	total: 1.82s	remaining: 44.6ms
1513:	learn: 0.5491367	total: 1.82s	remaining: 43.4ms
1514:	learn: 0.5489081	total: 1.82s	remaining: 42.2ms
1515:	learn: 0.5487628	total: 1.82s	remaining: 40.9ms
1516:	learn: 0.5487023	total: 1.83s	remaining: 39.7ms
1517:	learn: 0.5484318	total: 1.83s	remaining: 38.5ms
1518:	learn: 0.5481712	total: 1.83s	remaining: 37.3ms
1519:	learn: 0.5479119	total: 1.83s	remaining: 36.1ms
1520:	learn: 0.5475511	total: 1.83s	remaining: 34.9ms
1521:	learn: 0.5472554	total: 1.83s	remaining: 33.7ms
1522:	learn: 0.5471755	total: 1.83s	remaining: 32.5ms
1523:	learn: 0.5469789	total: 1.83s	remaining: 31.3ms
1524:	learn: 0.5467587	total: 1.83s	remaining: 30.1ms
1525:	learn: 0.5464530	total: 1.84s	remaining: 28.9ms
1526:	learn: 0.5463713	total: 1.84s	remaining: 27.7ms
1527:	learn: 0.5462562	total: 1.84s	remaining: 26.5ms
1528:	learn: 0.5460715	total: 1.84s	remaining: 25.3ms
1529:	learn: 0.5459775	total: 1.84s	remaining: 24.1ms
1530:	learn: 0.5456187	total: 1.84s	remaining: 22.9ms
1531:	learn: 0.5455120	total: 1.84s	remaining: 21.7ms
1532:	learn: 0.5453806	total: 1.84s	remaining: 20.5ms
1533:	learn: 0.5452918	total: 1.85s	remaining: 19.3ms
1534:	learn: 0.5450753	total: 1.85s	remaining: 18.1ms
1535:	learn: 0.5447432	total: 1.85s	remaining: 16.8ms
1536:	learn: 0.5446436	total: 1.85s	remaining: 15.6ms
1537:	learn: 0.5442665	total: 1.85s	remaining: 14.4ms
1538:	learn: 0.5439628	total: 1.85s	remaining: 13.2ms
1539:	learn: 0.5437742	total: 1.85s	remaining: 12ms
1540:	learn: 0.5435912	total: 1.85s	remaining: 10.8ms
1541:	learn: 0.5432821	total: 1.85s	remaining: 9.62ms
1542:	learn: 0.5430024	total: 1.86s	remaining: 8.42ms
1543:	learn: 0.5427856	total: 1.86s	remaining: 7.22ms
1544:	learn: 0.5424405	total: 1.86s	remaining: 6.01ms
1545:	learn: 0.5423136	total: 1.86s	remaining: 4.81ms
1546:	learn: 0.5422129	total: 1.86s	remaining: 3.61ms
1547:	learn: 0.5421131	total: 1.86s	remaining: 2.4ms
1548:	learn: 0.5419890	total: 1.86s	remaining: 1.2ms
1549:	learn: 0.5419283	total: 1.86s	remaining: 0us

visualize_error(error, modelname)

visulaize_performance_of_the_model(pred, y_test, modelname)

visualize_prediction_on_traindata(pred_cbr_trn,  y_train, modelname)

From the Hyper-parameter tuned report we got Generalized Model.

print(f"Train Score : {r2_score(y_train, pred_cbr_trn)}, Test Score : {r2_score(y_test, pred)}")

Train Score : 0.8895729400948202, Test Score : 0.8691069481070737

Project Flow:

1) Imported dataset

2) Removed duplicates using pandas

3) Removed duplicates in Independent variable

4) We addressed the huge difference in Train and Test score of models.

5) We picked one best model i.e., CatBoost Regressor from the result of Normal Distribution graph.

6) Then, we started addressing the root cause of the problem by checking which record cause more errors in the dataset is noted. The process runs 'n' number of times and called those records as problamatic records and based on the count of failure of records the dataset is sorted in descending order.

7) To get a Generalized model the problamatic records were fed into training part i.e., 1st 80% of the sorted dataset and rest 20% of the sorted dataset into testing part.

8) This approach gives a generalized model(Optimal Fit) with Train score of 0.889 and Test score of 0.869.

9) This model is deployed in AWS ElasticBeanstalk with the help of Flask Module.